Restoration
-
SmokeGS-R: Physics-Guided Pseudo-Clean 3DGS for Real-World Multi-View Smoke Restoration
Abstract
Real-world smoke simultaneously attenuates scene radiance, adds airlight, and destabilizes multi-view appearance consistency, making robust 3D reconstruction particularly difficult. We present \textbf{SmokeGS-R}, a practical pipeline developed for the NTIRE 2026 3D Restoration and Reconstruction Track 2 challenge. The key idea is to decouple geometry recovery from appearance correction: we generate physics-guided pseudo-clean supervision with a refined dark channel prior and guided filtering, train a sharp clean-only 3D Gaussian Splatting source model, and then harmonize its renderings with a donor ensemble using geometric-mean reference aggregation, LAB-space Reinhard transfer, and light Gaussian smoothing. On the official challenge testing leaderboard, the final submission achieved \mbox{PSNR $=15.217$} and \mbox{SSIM $=0.666$}. After the public release of RealX3D, we re-evaluated the same frozen result on the seven released challenge scenes without retraining and obtained \mbox{PSNR $=15.209$}, \mbox{SSIM $=0.644$}, and \mbox{LPIPS $=0.551$}, outperforming the strongest official baseline average on the same scenes by $+3.68$ dB PSNR. These results suggest that a geometry-first reconstruction strategy combined with stable post-render appearance harmonization is an effective recipe for real-world multi-view smoke restoration. The code is available at this https URL.
Abstract (translated)
真实世界中的烟雾会同时衰减场景辐射度、增加大气光并破坏多视角外观一致性，使得鲁棒的3D重建尤为困难。我们提出了\textbf{SmokeGS-R}，一个为NTIRE 2026 3D Restoration and Reconstruction Track 2挑战赛开发的实用流程。核心思想是将几何恢复与外观校正解耦：我们通过改进的暗通道先验和引导滤波生成物理引导的伪清洁监督数据，训练一个锐利的纯清洁3D高斯泼溅源模型，然后利用几何平均参考聚合、LAB空间Reinhard传递和轻量高斯平滑，通过捐赠者集成协调其渲染结果。在官方挑战测试排行榜上，最终提交结果达到了\mbox{PSNR $=15.217$}和\mbox{SSIM $=0.666$}。在RealX3D公开发布后，我们在未重新训练的情况下，对已发布的七个挑战场景重新评估了同一冻结结果，获得了\mbox{PSNR $=15.209$}、\mbox{SSIM $=0.644$}和\mbox{LPIPS $=0.551$}，在同一场景上比最强官方基线平均提升了$+3.68$ dB PSNR。这些结果表明，结合几何优先的重建策略与稳定的后渲染外观协调，是处理真实世界多视角烟雾恢复的有效方案。代码可在以下链接获取：this https URL。
URL
https://arxiv.org/abs/2604.05301
PDF
-
OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
2026-04-06 21:24:21Ali Aliev, Kamil Garifullin, Nikolay Yudin, Vera Soboleva, Alexander Molozhavenko, Ivan Oseledets, Aibek Alanov, Maxim RakhubaAbstract
In a rapidly growing field of model training there is a constant practical interest in parameter-efficient fine-tuning and various techniques that use a small amount of training data to adapt the model to a narrow task. However, there is an open question: how to combine several adapters tuned for different tasks into one which is able to yield adequate results on both tasks? Specifically, merging subject and style adapters for generative models remains unresolved. In this paper we seek to show that in the case of orthogonal fine-tuning (OFT), we can use structured orthogonal parametrization and its geometric properties to get the formulas for training-free adapter merging. In particular, we derive the structure of the manifold formed by the recently proposed Group-and-Shuffle ($\mathcal{GS}$) orthogonal matrices, and obtain efficient formulas for the geodesics approximation between two points. Additionally, we propose a $\text{spectra restoration}$ transform that restores spectral properties of the merged adapter for higher-quality fusion. We conduct experiments in subject-driven generation tasks showing that our technique to merge two $\mathcal{GS}$ orthogonal matrices is capable of uniting concept and style features of different adapters. To the best of our knowledge, this is the first training-free method for merging multiplicative orthogonal adapters. Code is available via the $\href{this https URL}{link}$.
Abstract (translated)
在模型训练这一快速发展的领域中，人们始终对参数高效微调以及利用少量训练数据使模型适应特定任务的各种技术抱有实践兴趣。然而，一个悬而未决的问题是：如何将针对不同任务微调得到的多个适配器合并为一个，使其能在两项任务上都取得合理结果？具体而言，生成模型中主题适配器与风格适配器的合并问题仍未解决。本文旨在证明，在正交微调（OFT）场景下，可利用结构化正交参数化及其几何特性，获得免训练的适配器合并公式。特别地，我们推导了近期提出的分组与洗牌（$\mathcal{GS}$）正交矩阵构成的流形结构，并得到了两点间测地线近似的高效公式。此外，我们提出一种**谱恢复变换**，通过恢复合并适配器的谱特性实现更高质量的融合。我们在主题驱动生成任务中的实验表明，所提出的$\mathcal{GS}$正交矩阵合并方法能够融合不同适配器的概念与风格特征。据我们所知，这是首个针对乘法正交适配器的免训练合并方法。代码可通过$\href{this https URL}{链接}$获取。
URL
https://arxiv.org/abs/2604.05183
PDF
-
Your Pre-trained Diffusion Model Secretly Knows Restoration
2026-04-06 17:59:04Sudarshan Rajagopalan, Vishal M. PatelAbstract
Pre-trained diffusion models have enabled significant advancements in All-in-One Restoration (AiOR), offering improved perceptual quality and generalization. However, diffusion-based restoration methods primarily rely on fine-tuning or Control-Net style modules to leverage the pre-trained diffusion model's priors for AiOR. In this work, we show that these pre-trained diffusion models inherently possess restoration behavior, which can be unlocked by directly learning prompt embeddings at the output of the text encoder. Interestingly, this behavior is largely inaccessible through text prompts and text-token embedding optimization. Furthermore, we observe that naive prompt learning is unstable because the forward noising process using degraded images is misaligned with the reverse sampling trajectory. To resolve this, we train prompts within a diffusion bridge formulation that aligns training and inference dynamics, enforcing a coherent denoising path from noisy degraded states to clean images. Building on these insights, we introduce our lightweight learned prompts on the pre-trained WAN video model and FLUX image models, converting them into high-performing restoration models. Extensive experiments demonstrate that our approach achieves competitive performance and generalization across diverse degradations, while avoiding fine-tuning and restoration-specific control modules.
Abstract (translated)
预训练扩散模型推动了全合一图像恢复（AiOR）领域的显著进步，提供了更优的感知质量和泛化能力。然而，基于扩散的恢复方法主要依赖微调或Control-Net风格模块来利用预训练扩散模型的先验知识。本研究表明，这些预训练扩散模型本身固有恢复行为，可通过直接在文本编码器输出端学习提示词嵌入来激活。有趣的是，这种行为难以通过文本提示或文本词元嵌入优化有效获取。此外，我们发现朴素提示词学习不稳定，因为使用退化图像的前向加噪过程与反向采样轨迹不匹配。为解决此问题，我们在扩散桥框架内训练提示词，使训练与推理动态对齐，强制从噪声退化状态到清晰图像形成连贯的降噪路径。基于这些见解，我们提出在预训练的WAN视频模型和FLUX图像模型上使用轻量级学习提示词，将其转化为高性能恢复模型。大量实验表明，该方法在多种退化场景下均具有竞争力的性能与泛化能力，同时避免了微调及特定恢复控制模块的需求。
URL
https://arxiv.org/abs/2604.04924
PDF
-
MedROI: Codec-Agnostic Region of Interest-Centric Compression for Medical Images
2026-04-06 08:24:50Jiwon Kim, Ikbeom JangAbstract
Medical imaging archives are growing rapidly in both size and resolution, making efficient compression increasingly important for storage and data transfer. Most existing codecs compress full images/volumes(including non-diagnostic background) or apply differential ROI coding that still preserves background bits. We propose MedROI, a codec-agnostic, plug-and-play ROI-centric framework that discards background voxels prior to compression. MedROI extracts a tight tissue bounding box via lightweight intensity-based thresholding and stores a fixed 54byte meta data record to enable spatial restoration during decompression. The cropped ROI is then compressed using any existing 2D or 3D codec without architectural modifications or retraining. We evaluate MedROI on 200 T1-weighted brain MRI volumes from ADNI using 6 codec configurations spanning conventional codecs (JPEG2000 2D/3D, HEIF) and neural compressors (LIC_TCM, TCM+AuxT, BCM-Net, SirenMRI). MedROI yields statistically significant improvements in compression ratio and encoding/decoding time for most configurations (two-sided t-test with multiple-comparison correction), while maintaining comparable reconstruction quality when measured within the ROI; HEIF is the primary exception in compression-ratio gains. For example, on JPEG20002D (lv3), MedROI improves CR from 20.35 to 27.37 while reducing average compression time from 1.701s to 1.380s. Code is available at this https URL.
Abstract (translated)
医学影像档案的体量与分辨率正快速增长，使得高效压缩对存储与数据传输愈发重要。现有编解码器多对全图像/体数据（包含非诊断性背景区域）进行压缩，或采用仍保留背景比特的差分感兴趣区域（ROI）编码。我们提出MedROI——一个编解码器无关、即插即用的ROI中心化框架，可在压缩前剔除背景体素。MedROI通过轻量级基于强度的阈值法提取紧致的组织边界框，并存储固定54字节的元数据记录以支持解压时的空间还原。裁剪后的ROI随后可使用任意现有2D或3D编解码器进行压缩，无需修改架构或重新训练。 我们在ADNI数据集200例T1加权脑部MRI体数据上，使用涵盖传统编解码器（JPEG2000 2D/3D、HEIF）与神经压缩器（LIC_TCM、TCM+AuxT、BCM-Net、SirenMRI）的6种编解码配置评估MedROI。结果显示：在ROI内保持可比重建质量的前提下，MedROI在多数配置中显著提升压缩比并缩短编解码时间（经多重比较校正的双侧t检验）；HEIF在压缩比增益方面是主要例外。例如在JPEG2000 2D（lv3）配置中，MedROI将压缩比从20.35提升至27.37，同时将平均压缩时间从1.701秒降至1.380秒。 代码公开于此https链接。
URL
https://arxiv.org/abs/2604.04511
PDF
-
Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback
2026-04-06 06:59:14Jianglin Lu, Yuanwei Wu, Ziyi Zhao, Hongcheng Wang, Felix Jimenez, Abrar Majeedi, Yun FuAbstract
Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language models and large language models, offer promising restoration capabilities but suffer from significant efficiency bottlenecks due to reflection, rollback, and iterative tool searching. Moreover, their performance heavily depends on degradation recognition models that require extensive annotations for training, limiting their applicability in label-free environments. To address these limitations, we propose a policy optimization-based restoration framework that learns an lightweight agent to determine tool-calling sequences. The agent operates in a sequential decision process, selecting the most appropriate restoration operation at each step to maximize final image quality. To enable training within label-free environments, we introduce a novel reward mechanism driven by multimodal large language models, which act as human-aligned evaluator and provide perceptual feedback for policy improvement. Once trained, our agent executes a deterministic restoration plans without redundant tool invocations, significantly accelerating inference while maintaining high restoration quality. Extensive experiments show that despite using no supervision, our method matches SOTA performance on full-reference metrics and surpasses existing approaches on no-reference metrics across diverse degradation scenarios.
Abstract (translated)
复杂图像恢复旨在从受模糊、噪声、雨滴及压缩伪影等多重退化影响的输入中重建高质量图像。近期基于视觉语言模型与大语言模型的恢复智能体虽展现出前景，却因反思、回退及迭代工具搜索等操作面临显著效率瓶颈。此外，其性能高度依赖需要大量标注数据训练的退化识别模型，限制了在无标注环境中的适用性。为应对这些局限，本文提出一种基于策略优化的恢复框架，通过学习轻量级智能体来确定工具调用序列。该智能体在序列决策过程中运作，每一步选择最合适的恢复操作以最大化最终图像质量。为实现在无标注环境中的训练，我们引入一种由多模态大语言模型驱动的新型奖励机制——此类模型作为与人类认知对齐的评估者，为策略优化提供感知反馈。训练完成后，我们的智能体执行确定性恢复方案，避免冗余工具调用，在保持高恢复质量的同时显著加速推理过程。大量实验表明，尽管无需任何监督信号，本方法在全参考指标上达到与当前最优技术相当的性能，并在多样退化场景的无参考指标上超越现有方法。
URL
https://arxiv.org/abs/2512.18599
PDF
-
Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
2026-04-06 04:51:44Wei Dai, Haoyu Wang, Honghao Chang, Lijun He, Fan Li, Jian Sun, Haixia BiAbstract
Vision Language Model (VLM) typically assume complete modality input during inference. However, their effectiveness drops sharply when certain modalities are unavailable or incomplete. Current research on missing modality primarily faces two dilemmas: Prompt-based methods struggle to restore missing yet indispensable features and degrade the generalizability of VLM. Imputation-based approaches, lacking effective guidance, are prone to generating semantically irrelevant noise. Restoring precise semantics while sustaining VLM's generalization remains challenging. Therefore, we propose a general missing modality restoration strategy in this paper. We introduce an enhanced diffusion model as a pluggable mid-stage training module to effectively restore missing features. Our strategy introduces two key innovations: (I) Dynamic Modality Gating, which adaptively leverages conditional features to guide the generation of semantically consistent features; (II) Cross-Modal Mutual Learning mechanism, which bridges the semantic spaces of the dual models to achieve bi-directional alignment. Notably, our strategy maintains the original integrity of the pre-trained VLM, requiring no fine-tuning of the backbone models while significantly boosting resilience to information loss. Zero-shot evaluations across benchmark datasets demonstrate that our approach consistently outperforms existing baselines, establishing it as a robust and scalable extension that ensures VLM reliability across diverse missing rates and conditions. Our code and models will be publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2602.03151
PDF
-
Rethinking Exposure Correction for Spatially Non-uniform Degradation
2026-04-05 14:41:59Ao Li, Jiawei Sun, Le Dong, Zhenyu Wang, Weisheng DongAbstract
Real-world exposure correction is fundamentally challenged by spatially non-uniform degradations, where diverse exposure errors frequently coexist within a single image. However, existing exposure correction methods are still largely developed under a predominantly uniform assumption. Architecturally, they typically rely on globally aggregated modulation signals that capture only the overall exposure trend. From the optimization perspective, conventional reconstruction losses are usually derived under a shared global scale, thus overlooking the spatially varying correction demands across regions. To address these limitations, we propose a new exposure correction paradigm explicitly designed for spatial non-uniformity. Specifically, we introduce a Spatial Signal Encoder to predict spatially adaptive modulation weights, which are used to guide multiple look-up tables for image transformation, together with an HSL-based compensation module for improved color fidelity. Beyond the architectural design, we propose an uncertainty-inspired non-uniform loss that dynamically allocates the optimization focus based on local restoration uncertainties, better matching the heterogeneous nature of real-world exposure errors. Extensive experiments demonstrate that our method achieves superior qualitative and quantitative performance compared with state-of-the-art methods. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.04136
PDF
-
NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results
2026-04-05 14:38:15Shuhong Liu, Chenyu Bao, Ziteng Cui, Xuangeng Chu, Bin Ren, Lin Gu, Xiang Chen, Mingrui Li, Long Ma, Marcos V. Conde, Radu Timofte, Yun Liu, Ryo Umagami, Tomohiro Hashimoto, Zijian Hu, Yuan Gan, Tianhan Xu, Yusuke Kurose, Tatsuya Harada, Junwei Yuan, Gengjia Chang, Xining Ge, Mache You, Qida Cao, Zeliang Li, Xinyuan Hu, Hongde Gu, Changyue Shi, Jiajun Ding, Zhou Yu, Jun Yu, Seungsang Oh, Fei Wang, Donggun Kim, Zhiliang Wu, Seho Ahn, Xinye Zheng, Kun Li, Yanyan Wei, Weisi Lin, Dizhe Zhang, Yuchao Chen, Meixi Song, Hanqing Wang, Haoran Feng, Lu Qi, Jiaao Shan, Yang Gu, Jiacheng Liu, Shiyu Liu, Kui Jiang, Junjun Jiang, Runyu Zhu, Sixun Dong, Qingxia Ye, Zhiqiang Zhang, Zhihua Xu, Zhiwei Wang, Phan The Son, Zhimiao Shi, Zixuan Guo, Xueming Fu, Lixia Han, Changhe Liu, Zhenyu Zhao, Manabu Tsukada, Zheng Zhang, Zihan Zhai, Tingting Li, Ziyang Zheng, Yuhao Liu, Dingju Wang, Jeongbin You, Younghyuk Kim, Il-Youp Kwak, Mingzhe Lyu, Junbo Yang, Wenhan Yang, Hongsen Zhang, Jinqiang Cui, Hong Zhang, Haojie Guo, Hantang Li, Qiang Zhu, Bowen He, Xiandong Meng, Debin Zhao, Xiaopeng Fan, Wei Zhou, Linzhe Jiang, Linfeng Li, Louzhe Xu, Qi Xu, Hang Song, Chenkun Guo, Weizhi Nie, Yufei Li, Xingan Zhan, Zhanqi Shi, Dufeng Zhang, Boyuan Tian, Jingshuo Zeng, Gang He, Yubao Fu, Weijie Wang, Cunchuan HuangAbstract
This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to identify robust reconstruction pipelines that are robust under real-world adverse conditions, specifically extreme low-light and smoke-degraded environments, as captured by our RealX3D benchmark. A total of 279 participants registered for the competition, of whom 33 teams submitted valid results. We thoroughly evaluate the submitted approaches against state-of-the-art baselines, revealing significant progress in 3D reconstruction under adverse conditions. Our analysis highlights shared design principles among top-performing methods and provides insights into effective strategies for handling 3D scene degradation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.04135
PDF
-
High-Fidelity Mural Restoration via a Unified Hybrid Mask-Aware Transformer
2026-04-05 06:09:47Jincheng Jiang, Qianhao Han, Chi Zhang, Zheng ZhengAbstract
Ancient murals are valuable cultural artifacts, but many have suffered severe degradation due to environmental exposure, material aging, and human activity. Restoring these artworks is challenging because it requires both reconstructing large missing structures and strictly preserving authentic, undamaged regions. This paper presents the Hybrid Mask-Aware Transformer (HMAT), a unified framework for high-fidelity mural restoration. HMAT integrates Mask-Aware Dynamic Filtering for robust local texture modeling with a Transformer bottleneck for long-range structural inference. To further address the diverse morphology of degradation, we introduce a mask-conditional style fusion module that dynamically guides the generative process. In addition, a Teacher-Forcing Decoder with hard-gated skip connections is designed to enforce fidelity in valid regions and focus reconstruction on missing areas. We evaluate HMAT on the DHMural dataset and a curated Nine-Colored Deer dataset under varying degradation levels. Experimental results demonstrate that the proposed method achieves competitive performance compared to state-of-the-art approaches, while producing more structurally coherent and visually faithful restorations. These findings suggest that HMAT provides an effective solution for the digital restoration of cultural heritage murals.
Abstract (translated)
古代壁画是珍贵的文化遗产，但许多因环境暴露、材料老化及人为活动而遭受严重退化。修复这些艺术品极具挑战性，因为既要重建大面积缺失结构，又需严格保留真实未损区域。本文提出了一种用于高保真壁画修复的统一框架——混合掩码感知Transformer（HMAT）。该框架集成了掩码感知动态滤波以 robust 建模局部纹理，并采用Transformer瓶颈进行长程结构推理。为应对多样化的退化形态，我们引入了掩码条件风格融合模块，动态引导生成过程。此外，设计了带硬门控跳跃连接的教师强制解码器，以强化有效区域的保真度并聚焦缺失区域的重建。我们在DHMural数据集及精选的《九色鹿》数据集上，针对不同退化程度评估了HMAT。实验结果表明，该方法与最先进技术相比具有竞争力，且能生成结构更连贯、视觉更忠实的修复结果。这些发现表明，HMAT为文化遗产壁画的数字修复提供了有效解决方案。
URL
https://arxiv.org/abs/2604.03984
PDF
-
Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement
2026-04-04 17:24:23Xuanzhao Dong, Wenhui Zhu, Xiwen Chen, Hao Wang, Xin Li, Yujian Xiong, Jiajun Cheng, Zhipeng Wang, Shao Tang, Oana Dumitrascu, Yalin WangAbstract
Over the past decade, generative models have demonstrated success in enhancing fundus images. However, the evaluation of these models remains a challenge. A benchmark for fundus image enhancement is needed for three main reasons:(1) Conventional denoising metrics such as PSNR and SSIM fail to capture clinically relevant features, such as lesion preservation and vessel morphology consistency, limiting their applicability in real-world settings; (2) There is a lack of unified evaluation protocols that address both paired and unpaired enhancement methods, particularly those guided by clinical expertise; and (3) An evaluation framework should provide actionable insights to guide future advancements in clinically aligned enhancement models. To address these gaps, we introduce EyeBench-V2, a benchmark designed to bridge the gap between enhancement model performance and clinical utility. Our work offers three key contributions:(1) Multi-dimensional clinical-alignment through downstream evaluations: Beyond standard enhancement metrics, we assess performance across clinically meaningful tasks including vessel segmentation, diabetic retinopathy (DR) grading, generalization to unseen noise patterns, and lesion segmentation. (2) Expert-guided evaluation design: We curate a novel dataset enabling fair comparisons between paired and unpaired enhancement methods, accompanied by a structured manual assessment protocol by medical experts, which evaluates clinically critical aspects such as lesion structure alterations, background color shifts, and the introduction of artificial structures. (3) Actionable insights: Our benchmark provides a rigorous, task-oriented analysis of existing generative models, equipping clinical researchers with the evidence needed to make informed decisions, while also identifying limitations in current methods to inform the design of next-generation enhancement models.
Abstract (translated)
过去十年间，生成模型在眼底图像增强领域已展现出显著成效。然而，这些模型的评估仍面临挑战。构建眼底图像增强基准测试主要基于三点需求：(1) 传统去噪指标（如PSNR与SSIM）无法捕捉病变保留、血管形态一致性等临床相关特征，限制了其在真实场景中的适用性；(2) 缺乏统一评估协议来同时处理有监督与无监督增强方法，特别是那些受临床经验指导的方法；(3) 评估框架应提供可操作的见解，以指导未来临床对齐增强模型的发展。为填补这些空白，我们推出EyeBench-V2基准测试，旨在弥合增强模型性能与临床效用之间的差距。本研究提供三项关键贡献：(1) 通过下游任务实现多维临床对齐：除标准增强指标外，我们在血管分割、糖尿病视网膜病变（DR）分级、对未知噪声模式的泛化能力及病变分割等临床相关任务中评估性能；(2) 专家引导的评估设计：我们整理 novel 数据集以实现有监督与无监督增强方法的公平对比，并配套医疗专家制定的结构化人工评估协议，该协议重点评估病变结构改变、背景色偏及人工结构引入等临床关键维度；(3) 可操作的见解：我们的基准测试对现有生成模型进行了严格的任务导向分析，既为临床研究人员提供决策依据，也揭示当前方法局限以指引下一代增强模型设计。
URL
https://arxiv.org/abs/2604.03806
PDF
-
HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing
2026-04-04 17:08:13Mohammad Heydari, Wei Dong, Shahram Shirani, Jun Chen, Han ZhouAbstract
Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly used in daytime dehazing. To address these challenges, we propose HistoFusionNet, a transformer-enhanced architecture tailored for nighttime image dehazing by combining histogram-guided representation learning with frequency-adaptive feature refinement. Built upon a multi-scale encoder-decoder backbone, our method introduces histogram transformer blocks that model long-range dependencies by grouping features according to their dynamic-range characteristics, enabling more effective aggregation of similarly degraded regions under complex nighttime lighting. To further improve restoration fidelity, we incorporate a frequency-aware refinement branch that adaptively exploits complementary low- and high-frequency cues, helping recover scene structures, suppress artifacts, and enhance local details. This design yields a unified framework that is particularly well suited to the heterogeneous degradations encountered in real nighttime hazy scenes. Extensive experiments and highly competitive performance of our method on the NTIRE 2026 Nighttime Image Dehazing Challenge benchmark demonstrate the effectiveness of the proposed method. Our team ranked 1st among 22 participating teams, highlighting the robustness and competitive performance of HistoFusionNet. The code is available at: this https URL
Abstract (translated)
夜间图像去雾由于同时存在雾霾、光晕、非均匀照明、色彩失真和传感器噪声等问题，仍是具有挑战性的底层视觉难题，这些因素常使白天去雾中常用的假设失效。为应对这些挑战，我们提出了HistoFusionNet——一种经Transformer增强的架构，通过结合直方图引导的表征学习与频率自适应特征精炼，专门针对夜间图像去雾设计。该方法基于多尺度编码器-解码器主干，引入了直方图Transformer模块，该模块依据动态范围特性对特征进行分组，从而对复杂夜间光照条件下相似退化区域进行更有效的聚合。为进一步提升复原保真度，我们融入了频率感知精炼分支，该分支自适应地利用互补的低频与高频线索，帮助恢复场景结构、抑制伪影并增强局部细节。这一设计形成了一个统一框架，特别适用于真实夜间雾景中遇到的异质退化问题。在NTIRE 2026夜间图像去雾挑战赛基准上的大量实验及极具竞争力的性能表现，验证了所提方法的有效性。我们的团队在22支参赛队伍中排名第一，凸显了HistoFusionNet的鲁棒性与竞争性。代码已公开于：此HTTPS链接。
URL
https://arxiv.org/abs/2604.03800
PDF
-
15 Years of Augmented Human Research: Where Do We Stand?
2026-04-04 12:42:42Steeven Villa, Abdallah El AliAbstract
The Augmented Human vision broadly seeks to improve or expand baseline human functioning through the restoration or extension of physical, intellectual, and social capabilities. However, given the rapid pace of technology development, we ask: what exactly does Augmented Human research involve, what are its core themes, and how has the Augmented Human(s) conference series evolved over time? To answer this, we conducted a scientometric analysis on the past 15 years of the Augmented Human(s) conference (N=735 paper), focusing on: geographical aspects, submissions and citation timelines, author frequency and popularity, and topic modeling. We find that: (a) Number of papers in the conference exhibit a bimodal distribution, peaking in 2015 and 2025, but showing periods of stagnant growth; (b) key topics over time include Haptics, Wearable Sensing, Vision & Eye Tracking, Embodied Interaction, and Sports / Motion; (c) some seminal papers on AH are not published in AH(s), but rather at related venues (e.g., CHI); (d) the conference has an active Japanese HCI community despite its historical Eurocentric location dominance. We contribute a closer look at the trajectory of the AH(s) field, and raise considerations of definitional and research scope ambiguities given the core problems/enhancements the field seeks to address.
Abstract (translated)
增强人类愿景 broadly 旨在通过恢复或扩展身体、智力和社会能力来改善或提升人类基础功能。然而，鉴于技术发展的 rapid pace，我们提出疑问：增强人类研究究竟涉及哪些内容？其核心主题是什么？以及增强人类会议系列随时间如何演变？为回答这些问题，我们对过去15年增强人类会议（N=735篇论文）进行了科学计量分析，重点关注：地理分布、投稿与引用时间线、作者频率与影响力、以及主题建模。研究发现：(a) 会议论文数量呈双峰分布，在2015年和2025年达到峰值，但存在增长停滞期；(b) 随时间演变的关键主题包括触觉反馈、可穿戴传感、视觉与眼动追踪、具身交互以及运动/体育；(c) 部分增强人类领域的开创性论文并未在增强人类会议发表，而是出现在相关会议（如CHI）上；(d) 尽管会议历史上以欧洲为中心，但日本HCI社区仍保持活跃。本研究深入审视了增强人类领域的发展轨迹，并就该领域试图解决的核心问题/增强目标所引发的定义模糊性与研究范畴争议提出思考。
URL
https://arxiv.org/abs/2604.03715
PDF
-
DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping
2026-04-03 19:04:36Soumendu Majee, Joshua Peter Ebenezer, Abhinau K. Venkataramanan, Weidi Liu, Thilo Balke, Zeeshan Nadir, Sreenithy Chandran, Seok-Jun Lee, Hamid Rahim SheikhAbstract
Smartphone cameras have gained immense popularity with the adoption of high-resolution and high-dynamic range imaging. As a result, high-performance camera Image Signal Processors (ISPs) are crucial in generating high-quality images for the end user while keeping computational costs low. In this paper, we propose DRIFT (Deep Restoration, ISP Fusion, and Tone-mapping): an efficient AI mobile camera pipeline that generates high quality RGB images from hand-held raw captures. The first stage of DRIFT is a Multi-Frame Processing (MFP) network that is trained using a adversarial perceptual loss to perform multi-frame alignment, denoising, demosaicing, and super-resolution. Then, the output of DRIFT-MFP is processed by a novel deep-learning based tone-mapping (DRIFT-TM) solution that allows for tone tunability, ensures tone-consistency with a reference pipeline, and can be run efficiently for high-resolution images on a mobile device. We show qualitative and quantitative comparisons against state-of-the-art MFP and tone-mapping methods to demonstrate the effectiveness of our approach.
Abstract (translated)
智能手机摄像头凭借高分辨率与高动态范围成像技术的普及而广受欢迎。因此，高性能的图像信号处理器（ISP）对于在保持低计算成本的同时向终端用户生成高质量图像至关重要。本文提出了一种名为DRIFT（深度复原、ISP融合与色调映射）的高效AI移动端摄像头成像管线，能够从手持RAW格式拍摄中生成高质量RGB图像。DRIFT的第一阶段是一个多帧处理（MFP）网络，该网络通过对抗性感知损失进行训练，以实现多帧对齐、去噪、去马赛克和超分辨率处理。随后，DRIFT-MFP的输出会经过一种新型的基于深度学习的色调映射（DRIFT-TM）方案处理，该方案具备色调可调性，能确保与参考管线保持色调一致性，并且可在移动设备上高效运行高分辨率图像。我们通过定性与定量对比当前最先进的多帧处理与色调映射方法，验证了本方法的有效性。
URL
https://arxiv.org/abs/2604.03402
PDF
-
VOSR: A Vision-Only Generative Model for Image Super-Resolution
2026-04-03 17:50:29Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Xiangtao Kong, Jixin Zhao, Shihao Wang, Lei ZhangAbstract
Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image data. While effective, this paradigm starts from a generic T2I generator, despite that SR is fundamentally a low-resolution (LR) input-conditioned image restoration task. In this work, we investigate whether an SR model trained purely on visual data can rival T2I-based ones. To this end, we propose VOSR, a Vision-Only generative framework for SR. We first extract semantically rich and spatially grounded features from the LR input using a pretrained vision encoder as visual semantic guidance. We then revisit classifier-free guidance for training generative models and show that the standard unconditional branch is ill-suited to restoration models trained from scratch. We therefore replace it with a restoration-oriented guidance strategy that preserves weak LR anchors. Built upon these designs, we first train a multi-step VOSR model from scratch and then distill it into a one-step model for efficient inference. VOSR requires less than one-tenth of the training cost of representative T2I-based SR methods, yet in both multi-step and one-step settings, it achieves competitive or even better perceptual quality and efficiency, while producing more faithful structures with fewer hallucinations on both synthetic and real-world benchmarks. Our results, for the first time, show that high-quality generative SR can be achieved without multimodal pretraining. The code and models can be found at this https URL.
Abstract (translated)
近期大多数生成式图像超分辨率（SR）方法依赖于在超大规模文本-图像数据上预训练的文本到图像（T2I）扩散模型。尽管有效，但该范式从通用T2I生成器出发，而超分辨率本质上是一个基于低分辨率（LR）输入条件的图像恢复任务。在本研究中，我们探索了仅通过视觉数据训练的SR模型是否能与基于T2I的方法相竞争。为此，我们提出了VOSR——一个面向超分辨率的纯视觉生成框架。我们首先使用预训练的视觉编码器从LR输入中提取语义丰富且空间定位的特征，作为视觉语义引导。随后，我们重新审视了生成模型训练中的无分类器引导方法，并证明标准的无条件分支不适合从零开始训练的恢复模型。因此，我们采用了一种面向恢复的引导策略来保留弱LR锚点。基于这些设计，我们首先从零开始训练多步VOSR模型，再将其蒸馏为单步模型以实现高效推理。VOSR的训练成本不到代表性T2I型SR方法的十分之一，但在多步和单步设置下均实现了具有竞争力甚至更优的感知质量和效率，同时在合成和真实世界基准测试中产生了更忠实结构且更少幻觉的结果。我们的研究首次表明，无需多模态预训练即可实现高质量生成式超分辨率。代码与模型可通过此https链接获取。
URL
https://arxiv.org/abs/2604.03225
PDF
-
Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks
2026-04-03 14:33:29Weixiong Sun, Xiang Yin, Chao DongAbstract
Recent advances in generative AI raise the question of whether general-purpose image editing models can serve as unified solutions for image restoration. In this work, we conduct a systematic evaluation of Nano Banana 2 for image restoration across diverse scenes and degradation types. Our results show that prompt design plays a critical role, where concise prompts with explicit fidelity constraints achieve the best trade-off between reconstruction accuracy and perceptual quality. Compared with state-of-the-art restoration models, Nano Banana 2 achieves superior performance in full-reference metrics while remaining competitive in perceptual quality, which is further supported by user studies. We also observe strong generalization in challenging scenarios, such as small faces, dense crowds, and severe degradations. However, the model remains sensitive to prompt formulation and may require iterative refinement for optimal results. Overall, our findings suggest that general-purpose generative models hold strong potential as unified image restoration solvers, while highlighting the importance of controllability and robustness. All test results are available on this https URL.
Abstract (translated)
生成式AI的最新进展引发了这样一个问题：通用图像编辑模型能否作为图像修复的统一解决方案。在本研究中，我们对Nano Banana 2在多样场景和退化类型下的图像修复能力进行了系统评估。结果表明，提示词设计起着关键作用——简洁且包含明确保真度约束的提示词能在重建精度与感知质量间取得最佳平衡。与最先进的修复模型相比，Nano Banana 2在全参考指标上表现更优，同时在感知质量方面保持竞争力，这一点也得到用户研究的佐证。我们还观察到该模型在挑战性场景（如小人脸、密集人群和严重退化）中展现出强大泛化能力。然而，模型仍对提示词表述敏感，可能需要通过迭代调整才能获得最优结果。总体而言，我们的发现表明通用生成模型作为统一图像修复解决方案具有巨大潜力，同时也凸显了可控性与鲁棒性的重要性。所有测试结果已公开于该链接。
URL
https://arxiv.org/abs/2604.03061
PDF
-
GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model
2026-04-03 13:47:57Qida Cao, Xinyuan Hu, Changyue Shi, Jiajun Ding, Zhou Yu, Jun YuAbstract
This paper describes our method for Track 2 of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge on smoke-degraded images. In this task, smoke reduces image visibility and weakens the cross-view consistency required by scene optimization and rendering. We address this problem with a multi-stage pipeline consisting of image restoration, dehazing, MLLM-based enhancement, 3DGS-MCMC optimization, and averaging over repeated runs. The main purpose of the pipeline is to improve visibility before rendering while limiting scene-content changes across input views. Experimental results on the challenge benchmark show improved quantitative performance and better visual quality than the provided baselines. The code is available at this https URL. Our method achieved a ranking of 1 out of 14 participants in Track 2 of the NTIRE 3DRR Challenge, as reported on the official competition website: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.03039
PDF
-
Task-Guided Prompting for Unified Remote Sensing Image Restoration
2026-04-03 05:29:12Wenli Huang, Yang Wu, Xiaomeng Xin, Zhihong Liu, Jinjun Wang, Ye DengAbstract
Remote sensing image restoration (RSIR) is essential for recovering high-fidelity imagery from degraded observations, enabling accurate downstream analysis. However, most existing methods focus on single degradation types within homogeneous data, restricting their practicality in real-world scenarios where multiple degradations often across diverse spectral bands or sensor modalities, creating a significant operational bottleneck. To address this fundamental gap, we propose TGPNet, a unified framework capable of handling denoising, cloud removal, shadow removal, deblurring, and SAR despeckling within a single, unified architecture. The core of our framework is a novel Task-Guided Prompting (TGP) strategy. TGP leverages learnable, task-specific embeddings to generate degradation-aware cues, which then hierarchically modulate features throughout the decoder. This task-adaptive mechanism allows the network to precisely tailor its restoration process for distinct degradation patterns while maintaining a single set of shared weights. To validate our framework, we construct a unified RSIR benchmark covering RGB, multispectral, SAR, and thermal infrared modalities for five aforementioned restoration tasks. Experimental results demonstrate that TGPNet achieves state-of-the-art performance on both unified multi-task scenarios and unseen composite degradations, surpassing even specialized models in individual domains such as cloud removal. By successfully unifying heterogeneous degradation removal within a single adaptive framework, this work presents a significant advancement for multi-task RSIR, offering a practical and scalable solution for operational pipelines. The code and benchmark will be released at this https URL.
Abstract (translated)
遥感图像恢复（RSIR）对于从退化观测中复原高保真图像、实现准确的下游分析至关重要。然而，现有方法大多聚焦于同质数据中的单一退化类型，限制了其在真实场景中的实用性——真实场景中常存在跨越不同光谱波段或传感器模态的多种退化问题，形成了显著的操作瓶颈。为应对这一根本性缺口，我们提出了TGPNet，一个能够统一处理去噪、去云、去阴影、去模糊及SAR相干斑抑制的单一架构框架。该框架的核心是一种新颖的任务引导提示（TGP）策略：TGP利用可学习的任务特定嵌入生成退化感知提示，进而在解码器中逐层调制特征。这种任务自适应机制使网络能在保持单一共享权重的同时，针对不同退化模式精确定制其恢复过程。为验证框架有效性，我们构建了涵盖RGB、多光谱、SAR与热红外模态的统一RSIR基准，覆盖上述五项恢复任务。实验结果表明，TGPNet在统一多任务场景及未见复合退化任务中均达到最优性能，甚至在云去除等特定领域超越了专业模型。通过成功将异质退化去除整合于单一自适应框架，本研究为多任务RSIR带来重大进展，为实际应用流程提供了实用且可扩展的解决方案。代码与基准数据集将在此链接公开发布。
URL
https://arxiv.org/abs/2604.02742
PDF
-
GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement
2026-04-02 09:45:58Xiaobin Rong, Yushi Wang, Zheng Wang, Jing LuAbstract
We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge. The system integrates a generative branch, which performs full-stack speech restoration in a self-supervised representation domain and reconstructs the waveform via a neural vocoder, along with a predictive branch that performs spectrogram-domain enhancement, providing complementary cues. Outputs from both branches are fused by a post-processing module, which also performs bandwidth extension to generate the enhanced waveform at 48 kHz, later downsampled to the original sampling rate. This generative-predictive fusion improves robustness and perceptual quality, achieving top performance in the blind-test phase and ranking 1st in the objective evaluation. Audio examples are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.01832
PDF
-
Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoising
2026-04-02 08:29:54Jigang Duan, Genwei Ma, Xu Jiang, Wenfeng Xu, Ping Yang, Xing ZhaoAbstract
Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent across different noise levels, leading to degraded restoration quality under mismatch between training and inference. To address this issue, we propose a quantitative flow matching framework for adaptive image denoising. The method first estimates the input noise level from local pixel statistics, and then uses this quantitative estimate to adapt the inference trajectory, including the starting point, the number of integration steps, and the step-size schedule. In this way, the denoising process is better aligned with the actual corruption level of each input, reducing unnecessary computation for lightly corrupted images while providing sufficient refinement for heavily degraded ones. By coupling quantitative noise estimation with noise-adaptive flow inference, the proposed method improves both restoration accuracy and inference efficiency. Extensive experiments on natural, medical, and microscopy images demonstrate its robustness and strong generalization across diverse noise levels and imaging conditions.
Abstract (translated)
扩散模型和基于流的生成模型在图像复原领域展现出巨大潜力。然而，在未知且变化的噪声条件下进行图像去噪仍具挑战性，因为学习到的向量场可能在不同噪声水平下变得不一致，导致训练与推理不匹配时复原质量下降。针对这一问题，我们提出了一种用于自适应图像去噪的定量流匹配框架。该方法首先从局部像素统计中估计输入噪声水平，然后利用这一定量估计来调整推理轨迹，包括起点、积分步数以及步长调度。通过这种方式，去噪过程能更好地与每张输入图像的实际退化程度对齐，对轻度退化图像减少不必要的计算，同时对重度退化图像提供充分的细化处理。通过将定量噪声估计与噪声自适应流推理相结合，所提方法在复原精度和推理效率上均得到提升。在自然图像、医学图像及显微图像上的大量实验表明，该方法在不同噪声水平和成像条件下具有鲁棒性和强泛化能力。
URL
https://arxiv.org/abs/2604.02392
PDF
-
Perturb-and-Restore: Simulation-driven Structural Augmentation Framework for Imbalance Chromosomal Anomaly Detection
2026-04-01 13:06:25Yilan Zhang, Hanbiao Chen, Changchun Yang, Yuetan Chu, Siyuan Chen, Jing Wu, Jingdong Hu, Na Li, Junkai Su, Yuxuan Chen, Ao Xu, Xin Gao, Aihua YinAbstract
Detecting structural chromosomal abnormalities is crucial for accurate diagnosis and management of genetic disorders. However, collecting sufficient structural abnormality data is extremely challenging and costly in clinical practice, and not all abnormal types can be readily collected. As a result, deep learning approaches face significant performance degradation due to the severe imbalance and scarcity of abnormal chromosome data. To address this challenge, we propose a Perturb-and-Restore (P&R), a simulation-driven structural augmentation framework that effectively alleviates data imbalance in chromosome anomaly detection. The P&R framework comprises two key components: (1) Structure Perturbation and Restoration Simulation, which generates synthetic abnormal chromosomes by perturbing chromosomal banding patterns of normal chromosomes followed by a restoration diffusion network that reconstructs continuous chromosome content and edges, thus eliminating reliance on rare abnormal samples; and (2) Energy-guided Adaptive Sampling, an energy score-based online selection strategy that dynamically prioritizes high-quality synthetic samples by referencing the energy distribution of real samples. To evaluate our method, we construct a comprehensive structural anomaly dataset consisting of over 260,000 chromosome images, including 4,242 abnormal samples spanning 24 categories. Experimental results demonstrate that the P&R framework achieves state-of-the-art (SOTA) performance, surpassing existing methods with an average improvement of 8.92% in sensitivity, 8.89% in precision, and 13.79% in F1-score across all categories.
Abstract (translated)
检测结构染色体异常对于遗传病的准确诊断和管理至关重要。然而，在临床实践中收集足够的结构异常数据极具挑战性且成本高昂，并非所有异常类型都能轻易获取。因此，由于异常染色体数据的严重不平衡和稀缺性，深度学习方法面临显著的性能下降。为应对这一挑战，我们提出了一种名为扰动-恢复（P&R）的模拟驱动结构增强框架，可有效缓解染色体异常检测中的数据不平衡问题。P&R框架包含两个关键组成部分：（1）结构扰动与恢复模拟，通过对正常染色体带型进行扰动生成合成异常染色体，并利用恢复扩散网络重建连续的染色体内容与边缘，从而消除对罕见异常样本的依赖；（2）能量引导的自适应采样，一种基于能量分数的在线选择策略，通过参考真实样本的能量分布，动态优先选择高质量合成样本。为评估该方法，我们构建了一个包含超过26万张染色体图像的综合性结构异常数据集，其中涵盖24个类别的4,242个异常样本。实验结果表明，P&R框架达到了最先进性能，在所有类别中分别以8.92%的灵敏度、8.89%的精确度和13.79%的F1分数超越了现有方法。
URL
https://arxiv.org/abs/2604.00854
PDF
