Point_Cloud
-
GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generation
2026-08-17 08:12:56Tianchen Deng, Xuefeng Chen, Shuang Wu, Qu Chen, Jiajun Zhu, Bo Dai, Jianfei Yang, Hesheng WangAbstract
Driving World Models (DWMs) have recently advanced rapidly with generative models, yet most existing methods mainly focus on conditional scene generation and lack explicit 3D scene understanding, language-grounded reasoning, and controllable 4D editing capabilities. Moreover, commonly used point cloud, occupancy, or BEV representations make it difficult to achieve fine-grained alignment between textual information and the underlying 3D scene structure. To address these limitations, we propose a foundation-feature Gaussian driving world model that unifies scene understanding, language-grounded reasoning, controllable 4D editing, and multi-modal generation within a single framework. Specifically, we introduce a foundation-feature Gaussian tokenizer that directly distills Qwen/SigLIP visual-language features into 3D Gaussian primitives, building a compact open-vocabulary Gaussian semantic field. We further design a geometry-aware Gaussian adapter that combines importance-aware hierarchical selection with text-conditioned Perceiver-style cross-attention to aggregate dense Gaussian primitives into compact world tokens. To improve representation compatibility, we introduce a KL-based Gaussian--image distribution alignment objective that aligns Gaussian world tokens with foundation image tokens. Based on the aligned Gaussian representation, our framework further supports instruction-controllable scene editing, including weather-conditioned generation and dynamic vehicle manipulation. Extensive experiments on broader driving benchmarks demonstrate that our method achieves state-of-the-art performance across scene understanding, visual grounding, planning-oriented reasoning, and controllable 4D generation tasks. We will release the code and datasets publicly on Github.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16234
PDF
-
PCT-Prompt: A Prompt-Guided Transformer Framework for Dense Prediction Tasks in Point Clouds
2026-08-17 08:01:33Dejun Zhang, Yanzi Bai, Yiqi WuAbstract
Standard Transformers have proven effective in point cloud object classification, but their performance in dense prediction tasks within complex scenes is often hindered by weak prior assumptions. To address this challenge, we propose PCT-Prompt, a novel framework that enhances standard Transformers by introducing a prompt-guided feature branch to improve performance in dense prediction tasks. The standard Transformer branch leverages pre-trained models for global feature extraction from point cloud data, serving as the backbone for processing high-level features. Meanwhile, the prompt-guided feature branch consists of two key components: a fine-grained feature extraction block that captures multi-scale geometric features using geometry-sensitive abstraction layer, along with the PnP-3D layer to integrate local context with global regularization. The second component, the prompt-refined feature learning block generates prompt tokens, which are subsequently refined through cross-attention mechanisms. Additionally, we introduce a prompt drop mechanism that progressively removes prompt information across Transformer layers, balancing local details and global consistency. Experimental results on the ShapeNetPart, S3DIS, and DALES datasets demonstrate that PCT-Prompt significantly improves the adaptability of standard Transformers to dense prediction tasks, achieving strong performance in real-world scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16225
PDF
-
VGGT-Align: Bridging Local Reconstruction and Global Consistency for Long-Sequence 3D Reconstruction
2026-08-15 14:32:55Wei Zhang, Yihang Wu, Songhua Li, Qi WangAbstract
Maintaining global geometric consistency is a central challenge in long-sequence 3D reconstruction, with scale drift being the most critical failure mode. In chunk-based inference pipelines, the scale degree of freedom in sequential Sim(3) alignment is left unconstrained, causing estimation errors to compound multiplicatively and distort global trajectories and point cloud geometry. We present a scale-consistency enhancement framework built on a key insight: in structured environments such as driving scenes, geometric quantities arising from environmental regularity remain inherently invariant across temporal segments, and discrepancies in their per-chunk measurements directly expose inter-chunk scale drift. We propose Scene Geometric Invariant Anchoring (SGIA), which extracts dominant geometric invariants from each chunk's predicted point cloud via coarse-to-fine robust estimation and exploits their cross-chunk consistency to establish scale constraints independent of point cloud registration, explicitly degenerating 7-DoF Sim(3) alignment into 6-DoF rigid-body transformation and severing chain-wise scale error propagation at its source. We further introduce a lightweight test-time adaptation strategy that fine-tunes only normalization-layer parameters via multi-objective self-supervision, progressively improving intra-chunk predictions along the sequence. Both modules are plug-and-play and require no offline retraining. Experiments on multiple long-sequence benchmarks demonstrate state-of-the-art performance, reducing absolute trajectory error by up to 32% with significant gains in trajectory stability and reconstruction quality. Code: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2608.15260
PDF
-
ProjFormer: Point Cloud Completion via Geometric-Projective Transformer and Cross-Modal Semantic Constraints
2026-08-15 08:05:48Sheng Liu, Meng Wang, Ruihui Li, Huilong Pi, Zhuo Tang, Kenli LiAbstract
Point cloud completion is inherently ill-posed due to severe sparsity and ambiguity in partial observations. Existing multi-view methods alleviate this by incorporating 2D semantics, but often rely on learned attention and fixed fusion, which lack geometric consistency and adaptability. We propose ProjFormer, a cross-modal framework that enforces geometry-consistent 2D-3D interaction through explicit projection and adaptive feature routing. A Projective Guided View Attention module aligns 3D points with multi-view features via deterministic projection, enabling efficient and geometrically consistent aggregation. Building on this, a geometry-aware routing network performs point-wise adaptive fusion of structural and observation-driven features for progressive refinement. Experiments show that, under a lightweight design, ProjFormer delivers competitive performance with improved structural completeness.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15104
PDF
-
GhostPoint: Self-Supervised Representation Learning by Hallucinating Occluded LiDAR Structure
2026-08-14 16:10:35Mohamed Abdelsamad, Bin Yang, Michael Ulrich, Miao Zhang, Yakov Miron, Alexandru Paul Condurache, Abhinav ValadaAbstract
3D object detection from LiDAR point clouds is a core problem in autonomous driving. Recent advances in self-supervised learning (SSL) enable scalable pretraining and transfers well to per-point tasks such as semantic and panoptic segmentation, but transfer to 3D detection remains weaker. We analyze recent SSL methods and find that most objectives are defined only on measured LiDAR returns from visible surfaces, leaving occluded and unobserved regions unconstrained. This visible-surface bias can be sufficient for point-wise prediction, but 3D detection requires robustness to missing structure. To address this gap, we propose GhostPoint, an SSL framework that hallucinates latent features in local neighborhoods around discovered instances, generated via a novel instance voxel dilation. In GhostPoint, an encoder processes observed returns, and an additional predictor infers neighborhood representations from observed context. In addition to standard encoder-level supervision, we introduce a predictor-level supervision scheme on sampled voxels from generated neighborhoods. Specifically, observed (visible/masked) voxels match teacher-encoder targets, while unobserved voxels match teacher-predictor hallucinations. This design encourages the learned representation to explicitly model structure beyond observed returns. Extensive evaluations on nuScenes and Waymo demonstrate that our method achieves state-of-the-art performance, consistently improving downstream 3D detection, especially under sparse scans and limited labels.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14428
PDF
-
IRGNN: Efficient Invariant Radar Graph Neural Network for Radar Point Cloud Object Detection
2026-08-14 15:35:06Xiao Guo, Wanke Xia, Lili Yang, Caicong WuAbstract
Perception is a fundamental component of autonomous driving systems. While LiDAR-based methods have achieved remarkable progress in object detection, their reliability can degrade under adverse weather conditions. Radar point clouds provide a robust alternative due to their resilience to bad weather and low-illumination scenarios. However, radar point clouds are typically sparse, unordered, and less informative than LiDAR data, making it challenging to directly apply existing LiDAR-based perception methods. To address these challenges, we propose IRGNN, an Invariant Radar Graph Neural Network for radar point cloud object detection. IRGNN first reconstructs radar point clouds into graph representations using translation- and rotation-invariant feature designs, enabling robust modeling of sparse radar measurements. It then employs an improved message passing neural network (MPNN) with residual connections and a virtual node layer to enhance local feature propagation and global context modeling. Finally, task-specific heads are applied to the learned graph representations for object classification and bounding box prediction. Experimental results on the RadarScenes dataset show that IRGNN outperforms existing radar-based object detection methods and achieves competitive performance. In addition, IRGNN significantly reduces computational cost and memory usage during inference, demonstrating its effectiveness and practical potential for efficient radar-based perception in autonomous driving.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14394
PDF
-
Accelerating Large-scale Bundle Adjustment for LiDAR Mapping via Parallel Computing
2026-08-14 12:43:05Yixi Cai, Rundong Li, Yuhan Xie, Qingwen Zhang, Patric Jensfelt, Fu ZhangAbstract
LiDAR bundle adjustment is widely utilized in mapping to construct globally consistent point cloud maps. In this paper, we propose the first fully parallel computing framework to accelerate LiDAR bundle adjustment for large-scale mapping, incorporating three key techniques. First, we design an adaptive, asynchronous data loading strategy to efficiently process large-scale point cloud datasets on memory-constrained GPUs. Secondly, we present a novel bottom-up voxelization method for extracting planar features, enabling fully parallelized pre-processing. Thirdly, we build upon a majorization-minimization formulation to accelerate compute-intensive tasks in the optimization via parallel computation, including the computation of residuals, Jacobian and Hessian matrices, and a parallel increment solver. To support our design, we provide both theoretical and experimental analysis of the time complexity of our approach. Extensive benchmarking on large-scale public datasets across various computational platforms validates the robustness and adaptability of our approach, achieving up to a tenfold improvement in computational efficiency while preserving mapping accuracy comparable to state-of-the-art methods. To benefit future research, the implementation code is available on GitHub.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14266
PDF
-
Can Language Models Understand mmWave Data? Benchmarking Large Language Models for mmWave Radar-Based Human Understanding
2026-08-14 10:49:39Jeongwan Shin, Jaehyeon Kim, Donguk Ko, Jaeho ChoiAbstract
Large language models (LLMs) have shown remarkable reasoning and generative capabilities, motivating their use as universal reasoning engines for perception. While modern approaches such as vision-language models (VLMs) have attempted to incorporate reasoning capabilities into visual sensing, the integration of LLMs with the millimeter-wave (mmWave) modality-despite its unique advantages under low light and occlusion-remains largely unexplored. The principal bottlenecks stem from the scarcity of radar language pairs, severe cross-dataset heterogeneity, and the absence of a foundational mmWave encoder. We address this gap through a minimal textualization interface that serializes each mmWave point cloud into concise natural language, allowing off-the-shelf LLMs to operate in a question answering (QA) setting. Building on this, we present mmWave-QA, the first benchmark for language-conditioned mmWave human perception. mmWave-QA aggregates heterogeneous public mmWave datasets and harmonizes them via calibration-aware preprocessing and global taxonomy alignment, while providing natural language QA. Spanning six scenarios and five QA tasks, the benchmark enables standardized evaluation across diverse mmWave hardware and experimental conditions, establishing a foundation for scalable research on mmWave-LLM integration. We further evaluate and analyze LLMs on our mmWave-QA, highlighting their zero-shot reasoning potential for radar perception, as well as their robustness under visual degradation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14179
PDF
-
FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects
2026-08-14 07:55:55Xingyu Zhu, Wenshuo Han, Zhouyu Wang, Yuran Wang, Ruihai Wu, Hao Dong, Fan Tang, Hechang Chen, Hyung Jin Chang, Yixing GaoAbstract
Robotic manipulation of flat objects is challenging due to the ungraspable configurations and strong variations in object geometry and material. Existing methods rely on heuristic pre-manipulation and are often evaluated in closed settings with limited generalization. We propose a unified framework that decouples the manipulation into a strategy generator and an action execution module. The strategy generator predicts appropriate manipulation strategies from object point clouds by learning strategy-centric, object-invariant representations via simulated data transformation and contrastive learning. Conditioned on the predicted strategy, the execution module decomposes long-horizon manipulation into reusable action primitives and dynamically composes them to generate stable trajectories. To enable systematic evaluation, we introduce FlatLab, a comprehensive simulation benchmark for robotic flat object manipulation. FlatLab provides high-fidelity physical simulation of diverse rigid and deformable flat objects, automated multi-modal data collection, and standardized task definitions and evaluation protocols. Experiments conducted in FlatLab demonstrate that our approach generalizes effectively to unseen objects and categories, outperforming existing baselines. The project page and the code are provided at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14049
PDF
-
Predictive Relative-Velocity Steering for Safe Robotic Manipulator Teleoperation in Dynamic Environments
2026-08-13 14:17:12Changhao Hu, Zeyi Liu, Songqiao Hu, Shuang Liu, Zihan Meng, Xiao HeAbstract
Recent advances in teleoperation have enabled robotic manipulators to perform dexterous, human-arm-like motions. However, human operators may fail to avoid suddenly appearing obstacles promptly and effectively, particularly under network latency or limited attention, thereby creating safety risks. To address this issue, we propose a lightweight and modular framework for proactive collision avoidance, operating directly at the end-effector velocity-command level. After preprocessing the point cloud, the framework first predicts potential collisions based on time-to-collision (TTC) with integrated overshoot protection, and subsequently rotates the relative-velocity vector using Rodrigues' rotation formula. The deflection changes only the direction of the relative velocity while preserving its magnitude, thereby mitigating the deadlock problem commonly encountered by conventional artificial potential field (APF) methods. The prediction module compensates for point-cloud processing latency introduced by complex teleoperation pipelines, while the lightweight design enables the high-frequency control required for teleoperation. Simulations across diverse scenarios show that the proposed method achieves a higher end-effector collision avoidance rate than the baseline methods. Experiments on a physical robotic system further validate its collision-avoidance effectiveness.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13284
PDF
-
Surface-to-Skeleton 3D Cephalometry: Estimating Hidden Skeletal Landmarks from CT-Derived External Soft-Tissue Surfaces
2026-08-12 19:09:57Tomoki Abe, Taiki Kanaya, Kazuki Saita, Mao Noda, Chie Tachiki, Yasushi Nishii, Hideo SaitoAbstract
Existing 3D facial-landmark methods localize points on visible skin, but whether CT-defined internal skeletal landmarks can be inferred from external soft-tissue geometry remains unclear. We formulate a coordinate-consistent surface-to-skeleton task using same-acquisition CT-derived surfaces, separating estimation from optical-to-CT registration, scanner-domain, and acquisition-state effects, with coverage analyzed separately. From 240 clinical CT scans from two hospitals, we construct a locked retrospective protocol pairing CT-derived external soft-tissue point clouds with 21 skeletal landmarks and three visible soft-tissue landmarks. An integrated hierarchical point-cloud model achieves 2.97 mm mean radial error on skeletal landmarks and 3.03 mm on deep or surface-invisible landmarks in 40 held-out patients. Patient-mismatch controls support patient-specific signal beyond a fixed population configuration or global similarity alone, while coverage ablations indicate dependence on non-anterior geometry. Optical-transfer diagnostics reveal substantial coverage-related and global-configuration components, although deployable optical inference remains unresolved. These results answer the controlled feasibility question affirmatively and provide a basis for hidden skeletal landmark inference.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12537
PDF
-
Boundary-Enhanced Segmentation of Pig Point Clouds in Commercial Housing Environments
2026-08-12 06:15:01Zhankang Xu, Fei Shi, Xiangyu Qi, Zhaoyang Wang, Mengxin Guo, Yikai Fan, Simon X. Yang, Qifeng Li, Weihong MaAbstract
In real pigsty environments, pig point clouds often come into close contact with background structures, resulting in blurred target boundaries, local adhesion, and background mis-segmentation. This reduces the accuracy of subsequent point cloud completion and body size measurement. To address these challenges, this study proposes a pig point cloud segmentation method based on boundary feature analysis. The proposed method adopts Octree Transformer as the backbone network and integrates local geometric details with global semantic context through octree convolution, self-attention encoding, and multi-scale feature fusion. Furthermore, soft-distance boundary pseudo-labels are generated to provide continuous boundary supervision, and a bidirectional cross-boundary semantic module is designed to enable explicit interaction between boundary and semantic features. Experiments conducted on a comprehensive dataset demonstrate that the proposed method significantly outperforms various state-of-the-art models in terms of segmentation accuracy, mean intersection over union, and boundary delineation. The results indicate that the method effectively alleviates boundary adhesion, providing reliable point cloud inputs for downstream precision livestock farming tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11697
PDF
-
Cloak of Invisibility: Real-Time Privacy-Preserving Volumetric Video Streaming
2026-08-12 04:44:20Hossein Khalili (UCLA), Philip Do (UCLA), Alexander Vilesov (UCLA), Kittipat Apicharttrisorn (Nokia Bell Labs), Nader Sehatbakhsh (UCLA)Abstract
Volumetric video streaming turns privacy into a 3D, multi-view problem. Unlike ordinary video, where sensitive content can often be redacted frame by frame, RGB-D volumetric pipelines capture people, rooms, and personal objects from multiple cameras and fuse them into a shared 3D representation. A private object missed in one view, or only partially removed before fusion, can therefore reappear in the reconstructed scene. This creates a privacy challenge for 3D telepresence, education, entertainment, and immersive applications: private content should be removed before raw visual and geometric data leave the camera side, while the public part of the scene should remain useful for real-time reconstruction. Existing volumetric streaming systems mainly optimize reconstruction, data movement, and latency, while privacy-preserving vision methods are designed for single-camera, single-frame images and do not directly address calibrated multi-view RGB-D fusion. We present InViStream, a real-time "privacy-from-source" system designed for this setting. InViStream addresses three challenges in volumetric capture: private objects may appear differently across views, RGB masking alone can leave geometric privacy leakage in depth, and public/private instances of the same class must be separated consistently before cloud-side fusion. To address these challenges, InViStream combines object detection with depth-aware masking, propagates public/private decisions across calibrated views, and fuses only sanitized point clouds. We evaluate InViStream on synthetic and real RGB-D scenes, including offices, conference rooms, living rooms, and settings with multiple public and private people and objects. InViStream achieves synthetic Dice/Recall of 0.799/0.891 and real Dice/Recall of 0.792/0.908, with synthetic SSIM above 0.98 and real-time streaming above 30 FPS.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11645
PDF
-
From Self-Normal-Positioning to Omni-Directional Tracking: Real-Time Surface Modeling Enabled Probe Tilt Control for Robotic Ultrasound Imaging
Abstract
Ultrasound (US) provides real-time, radiation-free imaging, but the image quality depends strongly on how the probe is oriented against the patient body. Robotic US can reduce operator workload and improve acquisition consistency; however, most existing systems focus on normal positioning, where the probe is maintained perpendicular to the local surface. This constraint is inadequate for examinations like echocardiography, where obtaining a diagnostic view requires a non-normal probe angle. Consequently, a clinically useful robotic system must sense the local surface in real-time and preserve the desired probe orientation. Here, we propose an omni-directional probe-orientation control framework that integrates RGB-D perception, local-surface modeling, and task-space orientation control. The surface model fuses multi-view point clouds and provides a quadratic estimate of the local surface. A desired imaging direction is then encoded relative to the normal, enabling the probe to track arbitrary angles. The framework was evaluated through flat-surface tracking, phantom target-angle recovery, and in-vivo tracking of an expert selected view. Results show that the mean angular tracking error was 1.06 +- 0.66 deg. The system recovered a non-normal tilt angle of up to 44.39 +- 2.59 deg relative to the surface normal, and acquired the desired heart chamber view in the phantom and in-vivo experiments.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11409
PDF
-
R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video
2026-08-11 15:00:15Ke Ma, Yamin Mao, Weiming Li, Shuai Tan, Yijie Zhong, Hao Chen, Haofen Wang, Meng WangAbstract
Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and transcript-based memories rarely preserve persistent object identity or structured spatial change. Existing long-video QA methods mainly emphasize temporal grounding and clip retrieval, while prior 3D scene-graph methods typically assume stronger geometry than free-motion wearable RGB video provides, including point clouds, RGB-D input, posed views, sparse reconstruction, or reconstructed scenes. R4DSG introduces a relative 4D scene graph memory for long egocentric video. Instead of storing raw graph sequences, R4DSG converts video into compact queryable memory entries indexed by time, place, persistent objects, anchor-relative change, and local interaction context. The main idea is to separate stable anchors from dynamic objects, maintain persistent object identity across frames, and represent object state through anchor-relative transitions rather than a globally aligned world model. Built on recent RGB-only advances in promptable video segmentation, temporal propagation, and relative 3D lifting, the method produces a retrieval-ready memory directly usable for long-horizon question answering. Evaluation on a 255-question object-related subset from EgoLifeQA shows, under question-only retrieval, a 6.7-point overall gain over EgoRAG-Text and a 12.5-point gain on when questions, which highlights the value of temporally organized object memory. These results position relative 4D scene graphs as a practical memory substrate for wearable assistants, AR systems, and embodied multimedia agents. GitHub Page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11017
PDF
-
Geometry-Based Compression of Plenoptic Point Clouds
2026-08-11 08:00:29Davi R. Freitas, Gustavo L. Sandri, Ricardo L. de QueirozAbstract
Plenoptic point clouds (PPC) are novel data structures that represent the light from different viewing directions in order to provide a higher degree of realism to regular point clouds. This is achieved by associating each point to multiple colors instead of a single one. Here, we present a method to efficiently compress the attributes of a PPC, consisting of a Karhunen-Loève transform over the color attributes followed by multiple attribute coders with intra prediction capability. This compression scheme can be incorporated within the MPEG's geometry-based PCC (G-PCC) standard, using any of G-PCC's existing solutions for attribute coding. Compression performance assessment using PPCs of different spatial resolutions reveals competitive results in comparison to existing methods, such as RAHT-based or video-based PCC solutions. We believe our coder to be the new state of the art.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11273
PDF
-
Real-World Cooperative Bimanual Dexterous Grasp of Large Objects from Single-View Observations
2026-08-11 02:24:27Ziming Li, Mingxuan Wu, Jiaqi Zhang, Hongfei Li, Yan Gan, Deqiang Ouyang, Ning WangAbstract
Bimanual dexterous grasping of large objects is a critical challenge in robotic manipulation. However, most existing studies focus on sequential manipulation rather than cooperative grasping, and methods addressing such bimanual tasks have largely been limited to simulation. These limitations stem from the difficulty of acquiring full 3D object models and generating physically plausible grasping actions. To fill this gap, we propose a real-world bimanual grasping framework that includes: a multimodal dataset capturing joint angles, visual observations and force signals; a Denoising Diffusion Probabilistic Model (DDPM)-based module that generates joint-level grasp configurations from segmented point clouds; and an execution strategy that integrates motion planning with online grasp refinement to ensure physical stability and feasibility. Our approach enables the synthesis of executable bimanual grasps from single-view inputs, reducing dependence on complete 3D object models and ensuring stable real-world performance. Experiments on a dual-arm robot demonstrate high success rates across unseen objects with varying geometries and poses, and ablation studies confirm the contributions of key components of our system.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10383
PDF
-
RoboSeg: Online Part-Level Semantic Reconstruction for Robotic Manipulation via a Single Eye-in-Hand Camera
2026-08-10 16:05:38Zhaochen Lan, Mengxiang LinAbstract
Robotic manipulation requires perception systemsthat identify actionable parts such as handles, rims, triggers,and tool tips, not merely object categories or point clouds. This paper presents RoboSeg, a part-level semantic reconstructionsystem that links vision-language model (VLM) functional-partdiscovery, asynchronous online RGB-D semantic reconstruc-tion, and task-oriented grasp generation without requiring CAD models or pre-scanned meshes. RoboSeg queries a VLM onthe initial RGB observation to obtain compact functional part prompts, then scans with two asynchronous streams: a high-frequency geometry thread for RGB-D odometry and truncated signed distance function (TSDF) fusion, and a keyframe-triggered semantic thread for SAM3 part masks. Projectedmasks are fused by voxel-level temporal voting into a persistentpart-labeled point cloud; RoboSeg uses this map to assign AnyGrasp 6-DoF candidates to semantic parts and select grasps consistent with the task-relevant part label. RoboSeg reaches 83.4% mean part intersection-over-union (mIoU) over manually labeled objects; in a 24-trial physical pilot across fourobjects and eight tasks, the selected grasp contacts the requestedpart in all trials and achieves 21/24 combined task this http URL results characterize RoboSeg as a semantic indexing layerfor task-conditioned manipulation, with AnyGrasp retained asthe proposal generator.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09778
PDF
-
TeaMatch: Teachable Cross-Modal Representation Learning for 2D-3D Matching
2026-08-10 13:24:01Chongjian Wang, Junjie GaoAbstract
Learning reliable correspondences between images and point clouds is fundamental for 2D-3D matching. Despite recent progress in detection-free methods, existing approaches primarily optimize matching within a single model and often struggle to maintain reliable correspondences under challenging conditions such as noisy inputs, low overlap, and ambiguous structures. In this work, we propose TeaMatch, a novel framework that introduces teachability as a criterion for cross-modal representation learning. We define teachability as the ability of a representation to be effectively recovered by weak learners under degraded inputs, reflecting its structural consistency and robustness. To this end, we construct a set of task-specific weak students that simulate common failure modes and train them to imitate the teacher on a training split while evaluating their recoverability on a disjoint meta split. The teacher is then optimized to improve the students' ability to recover reliable correspondences, guided by correspondence-level and geometry-aware constraints. Our framework can be seamlessly integrated into existing coarse-to-fine matching pipelines without additional inference cost. Extensive experiments demonstrate that TeaMatch improves matching robustness and achieves state-of-the-art performance on challenging 2D-3D matching benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09590
PDF
-
You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flows
2026-08-10 13:15:09Jonas Leo Mueller, Sebastian Hoefler, Dario Zanca, Naga Venkata Sai Jitin Jami, Thomas Altstidl, Bjoern M. EskofierAbstract
Sparse and noisy millimeter-wave radar point cloud observations often correspond to multiple plausible human poses, making deterministic pose estimation fundamentally ill-posed. Yet existing radar methods remain deterministic, collapsing this ambiguity into a single estimate. Diffusion-based alternatives can model multi-hypothesis distributions but require costly sequential denoising for each distribution sample and lack calibrated uncertainty. We propose Multi-Hypothesis Normalizing Flow Pose Generator (MH-NFPG), which models pose distributions from radar point clouds using a conditional normalizing flow. Specifically, we combine a spatiotemporal transformer backbone with a normalizing flow that transforms a Laplace base distribution into an expressive posterior, generated in parallel through a single forward pass. Leveraging this efficiency, we outperform diffusion-based alternatives in calibration across three radar benchmarks (MM-Fi, mmRadPose, mRI), improve pose accuracy on two, and match it on the third, while achieving over 20x faster inference for applications and reducing calibration error by up to 85%. We find that calibration degrades substantially for diffusion models, whereas our flow-based approach maintains reliable coverage, also in cross-environment settings. These results demonstrate normalizing flows as a practical alternative to diffusion models for real-time, uncertainty-aware radar pose estimation. Our code will be made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.09579
PDF
