arXiv_CV
-
HRoPE: Homography Relative Positional Encoding
2026-10-20 14:36:51Huachen Gao, Yang Yang, Xiaoqian Liang, Xingyu Chen, Youjia Zhang, Qi Zhang, Baorui Ma, Anpei Chen, Wei YangAbstract
Geometric Relative Positional Encoding has become the primary mechanism for injecting spatial inductive biases into multi-view transformers. Existing designs condition attention on camera-level frustums or ray-marched depth, associating cross-view tokens through the sensor geometry. Such sensor-centric formulations, however, describe only where a token is observed from, leaving the rich surface geometry of the scene region depicted by the token. In this paper, we advocate a shift toward surface-aware positional encoding that explicitly grounds patch tokens in the geometry of physical surfaces. We introduce HRoPE, which represents the local geometry of each patch as a slanted 3D plane, following the slanted support-window assumption of classical multi-view stereo. We inject token-level, plane-induced homographies into attention as relative transformations. This equips the transformer with a geometric prior for rectifying perspective distortions and aligning patch features across viewpoints. Our encoding requires no ground-truth geometry: the plane parameters can be predicted end-to-end under a view-synthesis objective alone, or derived from foundation models. Extensive experiments on RealEstate10K, CO3Dv2, and DL3DV show that our best variant of HRoPE consistently outperforms the evaluated geometric positional encodings for novel view synthesis. Extensive ablations and analysis show the effectiveness of the proposed encoding. Please refer to our project page at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.28284
PDF
-
Reliability-Aware Reconstruction of V-Shaped Surfaces with a Low-Cost Multi-Zone SPAD Sensor
Abstract
Low-cost multi-zone single-photon avalanche diode (SPAD) sensors provide compact time-of-flight measurements but are limited by sparse sampling and unreliable depth estimates near geometric discontinuities. This letter presents a reliability-aware reconstruction framework for V-shaped surfaces using two complementary TMF8821 acquisition configurations. Point-wise reliability is learned from sensor confidence, transient peak amplitude, and peak sharpness, and is incorporated into a graph-based depth optimization. The reconstructed geometry is evaluated by robust two-plane fitting and a perpendicular cross-section. Experiments on 60-degree, 90-degree, and 120-degree targets reduce the mean V-angle error from 11.21 degrees to 9.66 degrees (13.8%). For the representative 90-degree target, the combined point-to-plane RMSE decreases from 14.56 mm to 13.65 mm.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28258
PDF
-
SplatFlux: Feed-Forward 4D Gaussian Reconstruction and Generation from Video Latents
2026-10-20 14:12:53Runmin Zhang, Binglin Ren, Zhu Yu, Fudong Wang, Jiangke Lin, Yichun Shentu, Si-Yuan Cao, Yi Yuan, Hui-Liang ShenAbstract
This work presents SplatFlux, a feed-forward latent-to-4DGS framework for both video-based 4D reconstruction and conditional 4D generation. Our key observation is that observed videos and conditionally generated content can be represented in the same pretrained video latent space, allowing both tasks to be formulated as latent-to-4DGS decoding. To construct compact and temporally coherent 4D scenes, SplatFlux introduces a static-dynamic decoupled 4D Gaussian representation that explicitly predicts dynamic probabilities for Gaussian primitives. This representation separates static scene structures from moving regions, enabling complete 4D scene construction in a feed-forward manner through static aggregation and dynamic motion interpolation. To learn static-dynamic decomposition and dynamic Gaussian motion without costly annotations, we further develop an auxiliary distillation strategy that provides pseudo dynamic masks and optical-flow cues. Extensive experiments across 3D and 4D reconstruction and generation demonstrate that SplatFlux achieves state-of-the-art performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28257
PDF
-
Convergent Performance, Divergent Mechanisms in LoRA-Adapted Vision Foundation Models for Brain MRI
2026-10-20 14:12:44Cecilia Diana-Albelda, Fiona Kekwick, Raghav Mehta, Aleksandra Kulbaka, Paul M. Matthews, Jesus Bescos, \'Alvaro Garc\'ia-Mart\'in, Wenjia Bai, Bernhard KainzAbstract
Adapting Vision Foundation Models (VFMs) to medical imaging via LoRA has become standard practice, yet model selection is guided almost entirely by downstream task metrics, treating backbones with similar performance as interchangeable. We investigate whether equal performance implies equal internal representational shift. We analyse four ViT-B/16 backbones, DINOv3, SigLIP2, MerMED-FM, and BiomedCLIP, pre-trained with different objectives (self-distillation vs. contrastive vision-language) and on different data domains (natural vs. medical images). We adapt each to brain tumour segmentation and evaluate on six datasets covering both segmentation and Alzheimer's disease classification. Using attention divergence, weight-change analysis, and activation patching, we find that the four models converge to similar segmentation performance (mean Dice 78-81%) through markedly different internal dynamics, yet diverge in cross-task transfer: segmentation adaptation improves Alzheimer's disease classification for DINOv3 but degrades it for the other three backbones. We reveal a dissociation between modification magnitude and causal importance: the most heavily modified layers are not the causally relevant ones, with early-to-mid layers identified as sufficient for segmentation recovery. Restricting LoRA to these layers matches or approaches full-layer segmentation while reducing classification degradation in the three affected backbones, providing a mechanistically grounded strategy that is more parameter-efficient and more robust than standard full-layer adaptation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28255
PDF
-
Learn to Modify: Self-evolving Multi-agent Refinement Framework for Conversational Text-to-Motion Generation
2026-10-20 13:47:11Jianan Li, Jiawei Zhao, Yangtao Zhou, Zhifu Zhao, Shaoxin Wu, Yutao Wang, Dezhen Wang, Hua Chu, Fu LiAbstract
Despite rapid progress in text-to-motion generation, existing methods are commonly designed for single-shot generation. When users are dissatisfied with specific motion details, they are often forced to regenerate the entire sequence from scratch, which is computationally inefficient and potentially destroys previously established kinematic context. A practical generation system should instead support iterative user feedback and refine only the affected spatio-temporal regions while preserving the remaining motion. Therefore, we introduce a conversational motion generation paradigm that requires the system to coordinate instruction understanding, motion generation, localized editing, and quality assessment. Recent advances in LLM-driven multi-agent systems provide a promising foundation for such role-specialized coordination. To tackle these challenges, a Self-evolving Multi-Agent RefinemenT Framework (SMART) is proposed for conversational motion generation. Within SMART, to preserve semantic consistency, we design a semantic-guided masked motion editing mechanism, which precisely grounds natural language feedback into spatiotemporal motion regions to enable localized refinements without altering unedited regions. To reduce redundant exploration, we propose a memory-based self-evolving strategy that dynamically accumulates motion editing knowledge from interaction history and reuses past successful experience. Extensive experiments demonstrate that SMART effectively supports multi-turn conversational motion generation and enables efficient motion refinement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28210
PDF
-
Open-Form Geometric Style Transfer
2026-10-20 13:36:32Adar Elad, Gal Metzer, Omer Dahary, Min Lu, Daniel Cohen-OrAbstract
A geometric style learned from one family of shapes is typically applied to new shapes from the same family. We consider a more challenging setting: learning the geometric design language of a stylized Latin alphabet and applying it to new forms, from Greek glyphs to entirely different structures such as human poses. We introduce Open-Form Geometric Style Transfer, where the forms to which a learned geometric style can be applied are not restricted to the shape family in which that style was observed. This setting is deceptively challenging: the difficulty is not merely learning a style, but learning the style without learning the shape family in which it was observed. We represent target forms by structural sketches and disentangle structural adherence from style realization using a Geometry LoRA and a style-specific LoRA. Critically, open-form transfer requires the Geometry LoRA to be universal. To achieve this, we devise a geometry-enrichment strategy that constructs a large and purposefully diverse collection of synthetic structural sketches spanning a broad range of unfamiliar geometries. Our experiments and ablations demonstrate the importance of both disentanglement and this universal geometry prior, enabling geometric styles learned from glyphs, pictograms, and other shape families to be transferred to substantially different, unseen forms.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26820
PDF
-
Attractive Faces Skew Text-to-Image Reward Models and Leaderboards
Abstract
Human preference is now central to the evaluation, guidance, finetuning, and ranking of text-to-image models. However, the susceptibility of human preferences to bias in image generation remains underexplored. We identify a key observation: for human faces, perceived attractiveness overrides image quality in preference judgments, even when comparing real photographs of identical fidelity. In a controlled user study, annotators rank more attractive faces as higher quality, even when unattractive real faces are compared with attractive AI-generated ones. We examine the downstream consequences of this bias. Firstly, simulating Elo rankings from user study data shows attractiveness can invert a leaderboard's ranking, elevating synthetic attractive faces over real, unattractive ones. Secondly, the same bias reappears in the human preference models. Editing 40 annotated facial attributes in isolation, we find that attractiveness is the strongest correlate of score for four of five human preference models (PickScore, MPS, HPSv2.1, HPSv3), and the strongest predictor of score in regression analysis. We further show that preference aligned generation shifts faces toward younger, more feminine faces, and can override explicit prompts for unattractive faces, thereby limiting user control. Finally, we explore mitigation strategies, both for data collection and post training on human preference models. These findings highlight the need for preference models that disentangle image quality from human cognitive bias, enabling more reliable evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28195
PDF
-
Unified RAW Image Exposure Correction and Restoration via Linear Illumination and Frequency-Adaptive Enhancement
2026-10-20 13:31:28Yingkai Zhang, Yunhao Zou, Ying FuAbstract
Incorrect exposure degrades both image brightness and recoverable scene detail. Existing sRGB-based correction methods are limited by the non-linear image signal processing pipeline, whereas RAW-based methods are usually developed for a single degradation type, such as low-light denoising or high-light recovery. In this paper, we focus on joint exposure correction and restoration directly in the RAW domain and propose a unified RAW Image Exposure Correction and Restoration (RIECR) framework for both under- and over-exposed images. RIECR decomposes the problem into two coupled sub-problems that follow the RAW imaging model: linear illumination correction and residual degradation restoration. First, a Linear Illumination Correction Network (LICN) estimates exposure-aware linear gains by using channel-specific RAW cues. It exploits the high signal-to-noise ratio of Green channels for robust brightening and the relatively unsaturated Red/Blue responses for high-light darkening. Second, a dual-branch Frequency-based Enhancement Network (FEN) restores the remaining degradation with a Frequency Dynamic Convolution (FDC) module. FDC decomposes convolutional responses into low- and high-frequency components and adaptively suppresses amplified noise or recovers clipped textures according to the exposure context. We further build a real paired RAW benchmark containing 223 scenes and 1,784 pairs covering complex multi-exposure errors. Experiments against sixteen state-of-the-art methods show that RIECR achieves state-of-the-art performance on real RAW exposure correction.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28191
PDF
-
CrossFit-GS: Out-of-Fold Pose Estimation for COLMAP-Free 3D Gaussian Splatting
2026-10-20 13:29:26Zijian Wu, Jinliang Wang, Mingfeng Jiang, Zidian Lin, Ying Song, Ziqian LuAbstract
Pose-free 3D Gaussian Splatting (3DGS) aims to bypass cumbersome Structure-from-Motion (SfM) by directly reconstructing scenes from unposed image sequences. In this work, we present CrossFit-GS, a deferred-commitment progressive framework that mitigates cumulative trajectory drift and breaks the self-reinforcing loop of distorted-map error propagation. Specifically, we partition the input sequence into interleaved subsets and maintain two complementary submaps. Each candidate pose is cross-refined against a frozen opposite submap that has never been optimized using the target frame, thereby providing an independent geometric reference for pose estimation. Checkerboard validation and spatial coverage safeguards further reject unreliable updates, and only verified poses are committed to their corresponding owner submap. Once the trajectory has been refined, the intermediate submaps are discarded and the final global representation is trained from scratch using the fixed refined poses. Extensive evaluations across multiple benchmarks demonstrate that CrossFit-GS substantially reduces cumulative trajectory drift and consistently improves both camera pose estimation and novel-view synthesis over existing methods.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28190
PDF
-
CAPS: Clinically-Verifiable Anatomy-Prioritized Synthesis for Missing MRI Imputation in Brain Tumor Segmentation
2026-10-20 13:17:35Cecilia Diana-Albelda, Arthur Longuefosse, Mario Rub\'en Paz Campos, \'Alvaro Garc\'ia-Mart\'in, Jesus BescosAbstract
Multi-parametric MRI is the gold standard for neuro-oncology, yet acquiring complete 4-modality protocols may be unfeasible in real-world clinical practice. When handling missing modalities, existing automated systems force a critical compromise: robust segmenters operate as uninterpretable "black boxes" that bypass image generation, while standard synthesis models often produce blurry reconstructions lacking diagnostic reliability. To address this issue, we propose CAPS, a Clinically-Verifiable Anatomy-Prioritized Synthesis framework that reconciles computational precision with clinical transparency. Our multi-modal generative architecture is driven by a hybrid objective function (L_1 + L_AFP + L_DualDice) that explicitly enforces the preservation of deep anatomical features and strict topological boundaries, rather than relying solely on pixel-wise optimization. Evaluated comprehensively on the BraTS Adult Glioma dataset, the framework achieves superior synthesis fidelity across intensity-based metrics, and demonstrates robust downstream segmentation performance (82.38% mean Dice), successfully restoring verifiable visual context. Furthermore, the framework exhibits exceptional zero-shot cross-domain generalization, maintaining high structural fidelity across completely unseen Meningioma, Pediatric, and Sub-Saharan African cohorts without domain-specific adaptation. Finally, a blinded radiological assessment confirms that our anatomy-aware approach significantly enhances both perceived image quality and clinical utility, providing clinicians with the reliable visual evidence required to trust downstream automated workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28179
PDF
-
DocLayout-YOLO: Axis-Attentive Document Layout Detector with Mesh-Guided Synthetic Pretraining
2026-10-20 13:11:41Zhiyuan Zhao, Hengrui Kang, Guang Liang, Bin Wang, Conghui HeAbstract
Accurate and efficient document layout analysis is critical for modern document parsing systems. However, although the YOLO framework represents a leading paradigm for the real-time detector, its adaptation to heterogeneous documents remains underexplored. To address this gap, we propose DocLayout-YOLO, a document-specialized real-time detector that integrates diverse synthetic document pretraining and page-axis context modeling. From the data perspective, we introduce MeshLayout-1M, a synthetic pretraining corpus generated by the proposed Mesh-candidate BestFit algorithm, which provides large-scale and diverse document layouts for pretraining and improves adaptation to heterogeneous document scenarios. From the model perspective, we propose Page-Axis Layout Attention (PALA), which captures long-range dependencies along the horizontal and vertical page axes while remaining computationally efficient. Extensive experiments demonstrate that DocLayout-YOLO achieves state-of-the-art performance on four heterogeneous document benchmarks, obtaining 72.4%/75.5%/96.0%/73.1% mAP50:95 on D4LA, M6Doc, HJDataset, and PRIMA-LAD, respectively. Compared with existing real-time detectors, DocLayout-YOLO establishes a superior accuracy-efficiency trade-off in document layout analysis. Code, model, and data are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28171
PDF
-
OV-Foam: How 3D Representations Shape Semantic Feature Lifting
2026-10-20 12:38:14Yousef Rajeh (King Abdullah University of Science and Technology), Alejandra Esparza Pelcastre (Universidad Panamericana), Ivan Viola (King Abdullah University of Science and Technology), Dominik Engel (King Abdullah University of Science and Technology)Abstract
Existing feature lifting approaches for open-vocabulary segmentation rely on simple backprojection to assign features to primitives. In the case of 3D Gaussian splatting reconstruction, the primitives overlap heavily, leading to suboptimal reconstructions, governed by many primitives per ray. Backprojection, however, reduces to a least-squares solvable problem, exactly when no two primitives share a ray. Motivated by this insight, we propose OV-Foam, which uses PowerFoam as the underlying representation. This representation uses a power-diagram to partition the scene, resulting in zero overlap between primitives and a substantial reduction in primitives per ray, which ultimately simplifies the lifting problem and allows for closer-to-optimal feature assignment. We show that the space partitioning primitives of OV-Foam reach near-optimal assignment, and our experiments demonstrate improved open-vocabulary segmentation over Gaussian baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28131
PDF
-
GAMF-Net: Grouped Availability-Aware Multimodal Fusion for Smartphone Skin Lesion Classification
2026-10-20 12:35:39Yue Zhuo, Jingjia Yan, Fangyu Liu, Lingjun Liu, Zongjun Chen, Zhisheng Luo, Zhonghua XieAbstract
Smartphone clinical images provide a low-cost data source for computer-aided skin lesion classification in resource-constrained settings, but images alone cannot fully capture patients' medical histories and lesion symptoms. To address the lack of structured organization among heterogeneous clinical variables, the ambiguity between observed and imputed values, and the risk that clinical information may interfere with visual evidence, we propose GAMF-Net, a grouped availability-aware multimodal fusion network. Ten clinical variables are divided into three semantic groups---demographics, history-related risk, and lesion presentation---and each group jointly encodes field values and field-level availability masks. The image branch produces the base classification logits, while each clinical group generates image-conditioned class-level residual evidence. Only available groups participate in availability-normalized equal-weight fusion; when all clinical information is unavailable, the model reduces exactly to the image-only pathway. We evaluate the method on PAD-UFES-20 under a patient-disjoint five-fold protocol with separate training, validation, and test partitions. GAMF-Net achieves an Accuracy of $74.17\pm2.85\%$, a balanced accuracy (BACC) of $70.11\pm2.11\%$, a Macro-F1 of $68.85\pm0.85\%$, and a Macro-AUROC of $93.42\pm1.20\%$, outperforming all image-only and multimodal baselines reimplemented under a unified protocol. Compared with the strongest baseline, MetaBlock, the corresponding improvements are 2.37, 2.59, 4.14, and 1.02 percentage points, respectively. Ablation results show that clinical information substantially improves class-balanced performance, constrained equal-weight fusion is more effective than dynamic fusion, and the lesion-presentation group provides the most informative clinical complement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28129
PDF
-
PointForward V2: Point-Aligned Interaction for Feedforward Driving Reconstruction
2026-10-20 12:30:21Xianqi Wang, Cheng Chi, Yuechuan Pu, Hongcheng Luo, Junda Cheng, Guang Chen, Hangjun Ye, Bing Wang, Xin YangAbstract
Feedforward reconstruction of dynamic driving scenes requires integrating observations across multiple views and time steps into a coherent 3D representation. PointForward established state-of-the-art feedforward driving reconstruction by lifting image observations into sparse 3D queries, demonstrating the effectiveness of point-aligned scene representations. However, these queries are largely processed independently, limiting information exchange across space and time, while direct global attention among tens of thousands of point queries is computationally prohibitive. In this work, we present \textbf{PointForward V2}, which advances point-aligned representation to point-aligned interaction. Our key idea is to mediate query interaction through compact, scene-structured registers. For the static background, frame-wise Static Scene Registers compress point information, communicate across frames, and propagate the aggregated context back to the queries. For each dynamic instance, queries from different frames are aligned in an object-centric canonical space and interact through instance-specific Dynamic Instance Registers. We further employ 4D positional encoding that combines aligned spatial coordinates with original timestamps, enabling spatially aligned yet temporally distinguishable interactions. In this way, PointForward V2 enables scalable spatio-temporal reasoning directly among lifted 3D queries without dense global attention. Experiments on Waymo, nuScenes, and Argoverse 2 demonstrate state-of-the-art performance across large-scale driving benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28120
PDF
-
Reliability-Guided Vision-Language Decoding with Text-Aware Skip Refinement for Medical Image Segmentation
2026-10-20 12:29:44Sivan Talaei, Fatemeh Daneshfar, Mustaqeem Khan, Abdulhady Abas Abdullah, Mourad OussalahAbstract
Medical image segmentation remains challenging when targets exhibit limited visual distinction, irregular structure, or substantial variation across imaging modalities. Medical text can reduce this ambiguity, but indiscriminate fusion may introduce unreliable guidance. We present RELiF, a vision--language framework that integrates text through reliability-guided decoding. Its Reliability-guided Fusion Gate (RFG) adaptively controls cross-modal updates, while the Text-guided Skip Refinement Adapter (TSRA) refines high-resolution features using text guidance. RELiF is evaluated on radiographic, CT, and endoscopic segmentation tasks, where it shows competitive performance across diverse imaging characteristics and target appearances. Additional analyses examine efficiency and stability. The complementary uncertainty representation derived from the reliability response also shows an association with prediction difficulty, with higher uncertainty values occurring more frequently in pixels associated with segmentation errors. Code: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28118
PDF
-
LatticeRank: Spacing-Ranked Consistency for Native-Grid 3D Medical Image Segmentation
2026-10-20 12:08:51Jingjia Yan, Yue Zhuo, Zhonghua XieAbstract
Variable voxel spacing changes more than image resolution: it alters the discrete sampling lattice, tensor geometry, and anatomical evidence available to a 3D segmentation network. While conventional pipelines restore images to a canonical grid, direct-grid deployment requires the model itself to tolerate these changes. We observe that candidate grids are not exchangeable views -- a coarse grid removes more structural information than a mildly resampled one -- yet standard consistency objectives assign them equal influence. We therefore propose LatticeRank, a training-only framework that aligns candidate posteriors in physical space and allocates consistency supervision by voxel-spacing order: among endpoint-matched candidates, the auxiliary loss concentrates on the coarsest requested grid, while inference retains a single network forward with no candidate branch or ensemble. On MSD Task04, LatticeRank improves coarse-grid Extra Dice over mean consistency by 0.03436 across five seeds while meeting the prespecified reference-grid noninferiority criterion. A controlled ladder shows that grid exposure provides the largest recovery, posterior consistency adds a second gain, and spacing-ranked allocation yields the strongest direct-grid result; requested spacing thus provides a simple, model-independent ordering signal for direct-grid consistency learning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28091
PDF
-
WildAIGC-Bench: Can AI Image Detectors Handle the Wild? A Benchmark of Generated and Edited Images in Online Circulation
2026-10-20 12:07:16Zijian Yu, Hangwei Zhang, Jun Lan, Huijia Zhu, Weiqiang Wang, Jianfu ZhangAbstract
AI-generated images linked to news events and online claims can mislead audiences, enable fraud, or cause public controversy. We introduce WildAIGC-Bench, built through recurring collection across news websites, fact-checking sources, and related social media content. The pipeline combines broad coverage, timely updates, and human-verified labels through scheduled discovery, automatic screening and preliminary annotation, and human review of image-specific evidence. The benchmark contains 407 verified AI-generated or edited images, each accompanied by a source webpage link and an evidence summary. Images retain the conditions encountered online, including compression, screenshots, and recapture. Evaluation of dedicated visual detectors, multimodal large language models, and a simple Perception Encoder baseline reveals substantial recall gaps relative to existing benchmarks. WildAIGC-Bench provides both a practical detection challenge and a basis for continued data expansion and source-based verification. The dataset is released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28087
PDF
-
A Process-Informed, Photorealistic Digital Twin for Vision-Based Inline Inspection of C-SMC Strip Deposition
2026-10-20 11:38:13Patrick Flore, Fabian R\"oder, Kevin Chen, Andreas GebhardAbstract
Inline quality assurance for Sheet Molding Compound (SMC) manufacturing is hindered by the lack of large-scale, accurately labeled image datasets for training machine-learning models. This work presents a process-informed, photorealistic digital twin for carbon-fiber SMC strip deposition. A rigid-body simulation reproduces the deposition kinematics (settling, friction, belt motion), while a physically grounded polarization-rendering model produces realistic appearance, so that every image carries exact, mutually consistent labels in synchronized formats: oriented bounding boxes, point annotations, density maps, and polarization renderings (Angle and Degree of Linear Polarization). Because the joint distribution of many overlapping strips cannot be specified analytically, simulation yields exact, scalable ground truth that manual annotation cannot provide. The twin produces over 16,000 images across 3,300 frames, and the synthetic data replicate near-isotropic fiber orientation (axial concentration r < 0.05) consistent with as-deposited commercial SMC. Trained purely on synthetic data, YOLOv11 and CSRNet reach detection mAP50 up to 0.91, with a dedicated oriented-bounding-box detector confirming the oriented labels are directly trainable (mAP50 = 0.83); on real manufacturing images, the synthetic-to-real difference in edge and texture structure (Kolmogorov-Smirnov distance 0.46, distribution overlap 0.56) is of the same magnitude as the difference between two real acquisition series of the same material (0.41, overlap 0.57). The approach substantially reduces the labeling burden for camera-based inline inspection of fiber orientation and volume content.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28050
PDF
-
Spherical Geometry-Aware Panoptic Scene Graph Generation for Equirectangular Panoramas
2026-10-20 11:23:03Zhe Wu, Xiaoyan Fei, Xinyi Jiang, Yanxu Wei, Junming Rao, Yihong Yan, Xuewei LiAbstract
Panoptic scene graph generation (PSGG) represents scene entities with segmentation masks and directed relations. Equirectangular projection (ERP) panoramas challenge PSGG through distortion, latitude-dependent pixel areas, and an artificial seam. We propose a two-stage spherical geometry-aware framework that fuses overlapping perspective-view predictions using observation reliability, spherical overlap, and angular proximity. Relation reasoning combines spherical-area-aware aggregation, weighted no-relation supervision, and dual-longitude score fusion. We also construct a dataset of 340 high-resolution panoramas with 10,571 nodes and 6,632 directed relations. Against corresponding baselines, spherical fusion improves PQ by 36.03% under matched views, while relation reasoning improves mR@50 by 11.20% under PredCls with ground-truth masks and object labels. The full framework improves mR@50 by 52.99% under SGDet with predicted panoptic segments. These results demonstrate the value of spherical geometry for panoramic PSGG.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28033
PDF
-
LEVI: Benchmarking Visual Identity Fidelity with Verifiable Low-Entropy Constructs
Abstract
Modern generative models can produce visually plausible images while violating exact identity constraints. Evaluating such failures requires distinguishing violations of the requested identity from permissible variation in appearance. We introduce Low-Entropy Visual Identity (LEVI), which characterizes visual identities determined by compact facts and explicit rules. The low-entropy requirement concerns identity uncertainty, while appearance may remain diverse. We formulate identity fidelity in terms of the probability that a conditional image distribution assigns to the identities permitted by the prompt. Visual Identity Spaces (VIS) formalize this distinction by specifying admissible identity values and which different realizations express the same identity. Building on this formulation, we develop Verifiable Visual Grammar (VVG), a declarative language whose typed primitives and compositional constraints describe identity-bearing structures. Using this grammar, we build a benchmark for image generation. It assesses each output against the task's identity requirements, drawing evidence from the final pixels. The curated benchmark contains 1,375 tasks spanning 120 base identity spaces across six domains. Among ten evaluated model configurations, the highest whole-task pass rate is 58.69%. These results reveal a persistent gap between visually plausible images and faithful realization of their specified identities. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.25716
PDF
