Depth boundaries remain a major source of error in stereo matching. For IGEV on Scene Flow, geometric edge pixels account for only 6% of evaluated pixels but about half of the total absolute disparity error. Photometric edges can respond to texture changes without corresponding depth discontinuities, making them unreliable cues for boundary refinement. We propose E3Stereo, which learns geometric edges from disparity supervision and combines these boundary cues with the backbone disparity and image details to predict full-resolution disparity corrections. The same edge map also emphasizes boundary errors during training, while joint optimization allows the edge predictor to adapt to disparity refinement. On the Scene Flow dataset, E3Stereo reduces end-point error (EPE) at depth boundaries by 9.5%-14.3% across RAFT-Stereo, IGEV, and MonSter, while also reducing overall EPE. After fine-tuning, our IGEV-based model improves upon IGEV on all eleven reported metrics across ETH3D, KITTI 2012, and KITTI 2015. The source code will be made publicly available upon acceptance.
https://arxiv.org/abs/2610.33704
Typed decision-making tasks in agents, such as UI element selection, product recommendation, and chart matching, require models to choose from a set of discrete candidates. While prior work demonstrates that text-only System One models achieve four key properties including candidate-order invariance, scalability, and cache reuse via separate request-candidate encoding, extending them to multimodal settings where candidates are visual remains underexplored. We introduce Iris, a framework that accommodates image, text, or hybrid candidates while preserving the core decision module. We prove that order invariance and exact cache reuse hold for any per-candidate encoder under Iris, and derive the closed-form latency reduction. We construct a visual-candidate benchmark from Multimodal-Mind2Web (K=16, deduplicated, order-shuffled, three generalization splits). Independent encoding (Iris) achieves 78.4 / 72.1 / 74.8 percent accuracy with zero-flip rate under candidate reordering. Joint encoding reaches 90.6 / 89.5 / 91.6 percent but suffers an 8 to 10 percent answer-flip rate when shuffled. To bridge this gap, we propose a design that encodes each candidate conditioned on the request state without inter-candidate cross-attention; it preserves strict order invariance, enables forked cache sharing, and attains 91.7 / 86.5 / 90.0 percent accuracy at one-third of OneJev latency with calibrated null probabilities (AUROC 0.93 to 0.97). Reusing image candidates across requests cuts latency by 37x at K=256 and 191x at K=2048. On MetaEncoder benchmarks, Iris-4B achieves 100 percent on JevBench original and easy, outperforming 30B MetaEncoder and 27B OpenJev. Finally, we resolve a systems bottleneck on Ampere GPUs: reformulating Qwen3.5 patch-embedding Conv3d into its exact matrix-product form accelerates processing by 350x. Code, data, and checkpoints: this https URL.
https://arxiv.org/abs/2610.33702
Reconstructing a coherent 3D scene from uncurated image collections remains challenging due to the presence of irrelevant or non-overlapping views. Recent work has shown that feed-forward reconstruction models contain internal view-consistency signals that support distractor rejection. However, reference-conditioned filtering relies on a curated clean reference, which is not guaranteed in practical image collections. To address this limitation, we introduce FreeView, a training-free framework that jointly selects a filtering reference and rejects distractor views from an uncurated collection. FreeView leverages collection-level consensus to identify a representative view that serves as a reliable reference for filtering. It then adapts view rejection to each input collection by combining complementary visual and geometric evidence. This approach preserves useful views under substantial appearance and viewpoint variations while rejecting distractors. FreeView integrates with both VGGT and pi^3, removing the need for a manually curated reference or manual calibration of view rejection. Extensive experiments across multiple datasets demonstrate high clean-view retention and distractor rejection rates, leading to reliable 3D reconstruction from uncurated views.
https://arxiv.org/abs/2610.33656
Existing methods for CAD reconstruction from 3D scans achieve strong performance on standard benchmarks, yet their effectiveness often degrades in real-world scenarios where objects consist of multiple parts and scan artifacts such as noise. A key reason is that current CAD reconstruction datasets predominantly contain single-part models and clean geometric inputs, limiting the ability of learned models to generalize to realistic settings. In this work, we introduce CADonatello, a part-aware framework for reconstructing parametric CAD models from real-world 3D scans. Our approach first decomposes the input geometry into structurally meaningful components using a foundation-scale 3D part segmentation model, and then reconstructs each component independently through a cross-section-driven pipeline that performs sketch parameterization followed by an extrusion. To improve the robustness of sketch parameterization to scan-derived cross-sections, we further introduce CC3D Cross-Sections, a dataset of paired rasterized cross-section images from realistic scans and their corresponding parametric sketches derived from aligned CAD models. This dataset enables effective domain adaptation from clean CAD sketch images to scan-derived cross-section images. Extensive experiments demonstrate that the proposed approach improves generalization to noisy scans and enables reliable reconstruction of complex multi-part objects across multiple real-world CAD reverse engineering benchmarks.
https://arxiv.org/abs/2610.33575
Running a language model and a dense 3D map on one device means the two share one memory, and exceeding its limit is an out-of-memory failure. Map systems that keep a bounded working set bound it by a count of keyframes, but the memory one keyframe occupies varies widely with what it carries, so a count does not control what the working set occupies. The unit of admission is as poorly matched, since a radius around the pose, a fixed cell, or the graph neighbors of the last matched keyframe all move parts of the map that are not needed. We therefore propose two decisions. First, the memory the resident map uses is bounded directly, and the cost of every admission is known before any data is read, from per-keyframe resident sizes computed offline and carried with the map. Second, keyframes are admitted and released at a semantic spatial unit, the rooms and corridors of the building, so that the robot holds the zone it occupies together with the zone it is about to enter while the zones it has passed are released. Every admission measures the resident total, makes room, and only then reads, so the budget is never overshot. On two NVIDIA Jetson boards the budget holds in every run and the model gives up at most 0.8 percent of its throughput, whereas without it the operating system kills the model or the map. Under that budget, and over the environments evaluated, admission by semantic zone localizes 6-9 points more of the query frames than a geometric partition of matched zone count and about twice as much as the retrieval of RTAB-Map, at a lower ATE. Bounding memory lets the map and the model coexist, and moving the map in semantic zones makes the bounded map usable.
https://arxiv.org/abs/2610.33574
Video world models are expected to generate videos that accurately follow specified camera trajectories while maintaining consistent 3D structures. However, existing models are predominantly trained on densely sampled videos with small inter-frame camera motions. When applied to sparse, large step trajectories, they often produce frozen frames, inaccurate camera motion, and severe geometric drift. We attribute this degradation to a mismatch between the gradual viewpoint transitions seen during training and the large viewpoint changes required at inference time. To address this problem, we propose Dense Trajectory Teacher Distillation (DTTD), a post-training framework that transfers a model's generation capability from dense trajectories to large camera motions. Given a sparse trajectory, DTTD interpolates additional camera poses to construct a dense trajectory covering the same path. The frozen base model then generates reliable teacher videos along this familiar dense trajectory, and pose aligned teacher observations are used to evaluate candidate videos generated under the original sparse trajectory. In this way, the model serves as its own generation teacher, requiring neither additional video data nor a stronger external video generator. We further combine dense teacher supervision with geometry aware rewards that assess cross frame consistency and camera trajectory following, and use the resulting preferences for offline preference optimization. To stably expand the model's motion range, we introduce a cumulative curriculum that progressively incorporates larger motion steps while retaining simpler trajectories to reduce capability forgetting.
https://arxiv.org/abs/2610.33566
Video spatial reasoning requires multimodal large language models (MLLMs) to understand how objects are arranged and related across viewpoints. While these models can recognize objects in individual frames, integrating these observations to solve complex spatial tasks remains challenging. We examine route planning as a representative task and observe that existing models become substantially less accurate as the number of required turns increases, with several models achieving accuracy close to random guessing on routes requiring three or more turns. This finding suggests that recognizing landmarks alone is insufficient: models must also connect observations across viewpoints and track how landmarks are arranged in a shared space. Motivated by this observation, we introduce GeoLift, a training-free framework that uses feed-forward 3D reconstruction to map objects detected in individual frames into a shared metric 3D scene. GeoLift combines a frozen MLLM for 2D grounding with pretrained geometry models for scene reconstruction. It then uses shared geometric regions, called superpoints, to associate observations of the same object across views without a learned matcher. The reconstructed 3D map enables explicit computation of spatial relations and multistep routes, and provides geometric evidence for estimating distances and sizes. With all model weights frozen, GeoLift improves Qwen3-VL-4B's average score on VSI-Bench from 55.4% to 64.1%, including an increase in route-planning accuracy from 30.9% to 53.6%, and achieves 59.8% accuracy on MindCube. These results show that connecting frame-level object grounding through a shared 3D map can improve complex spatial reasoning without task-specific training.
https://arxiv.org/abs/2610.33558
Automated prostate lesion detection from diffusion-weighted MR imaging (DWI) conventionally relies on reconstructed images and does not fully use all acquisition information. We present an end-to-end network that uses complex multicoil DWI data and coil sensitivity information for prostate lesion segmentation. We included 269 fastMRI prostate examinations with additional voxel-level lesion annotations. Of these, 64 examinations contained PIRADS 4 or 5 lesions. The proposed network, VarNet-Seg, consists of a k-space variational network (VarNet) with six variational cascades and an image-space 3D segmentation U-Net. Comparator models used the same segmentation architecture with fully coil-combined images (CC-Seg), fixed root-sum-of-squares reconstruction (RSS-Seg), or fixed SENSE reconstruction (SENSE-Seg). We performed ablations with end-to-end training and data consistency (DC) enabled or disabled. We evaluated lesion segmentation using Dice and patient-level detection using AUROC in five-fold cross-validation with full sampling, simulated undersampling, added noise, or both. VarNet-Seg achieved the highest Dice at every undersampling level. At eight-fold acceleration, Dice was 0.22 for VarNet-Seg, 0.14 for SENSE-Seg and 0.16 for VarNet-Seg (no DC). The paired difference from SENSE-Seg was 0.08 (95% CI, 0.04-0.11). With full sampling, VarNet-Seg and RSS-Seg performed similarly (0.40 vs 0.39). Patient-level AUROC decreased from 0.75 with full sampling to 0.63 at eight-fold acceleration; corresponding RSS-Seg AUROCs were 0.76 and 0.64. The proposed multicoil network improved prostate lesion segmentation under simulated undersampling compared to conventional models. Matched ablations supported contributions from both end-to-end training and data consistency. Prospective evaluation is needed to establish whether this approach can be used clinically in accelerated prostate DWI.
https://arxiv.org/abs/2610.33554
Crack propagation provides richer information than static crack observations for evaluating structural conditions of concrete infrastructure and planning maintenance strategies. Unlike static crack detection, which can now be largely automated using computer vision, vision-based crack tracking is a coupled cross-view and cross-time problem: the same physical crack must retain its identity as camera viewpoints change, while newly developed growth must be distinguished from existing crack segments in a unified reference view. Existing segmentation and 3D reconstruction methods can recover crack masks or scene geometry, but they do not preserve crack identity across views or quantify temporal extension. To address this gap, this study formulates crack growth monitoring as a cross-view and cross-time crack-instance tracking task and proposes a geometry-assisted, morphology-aware framework. The framework first uses image-based geometric registration to align observations from different viewpoints into a shared structural reference, then applies morphology-aware instantiation to assign physically interpretable crack identities, and finally performs temporal mapping in the unified view to distinguish newly developed growth from existing crack segments. To enable evaluation, a temporally annotated dataset was established and used, covering three representative cracking scenarios: single dominant crack propagation, mixed-mode branching, and multiple-crack interaction, with pixel-level masks and cross-time instance labels. Experimental results show that the proposed framework can establish loose cross-view identity correspondence under changing viewpoints, while strict spatial overlap and growth localization remain limited by early micro-crack segmentability and projection drift, highlighting directions for future crack-monitoring research.
https://arxiv.org/abs/2610.33550
Recent vision-and-language navigation (VLN) policies act on their visual history, and an incorrect action can take them off the instructed route. Paired interventions on four VLN policies show that clearing the history doubles pooled success at the onset of a deviation but lowers it on route, while later in a deviation, removing only the off-route frames helps much less. After a deviation, the retained history keeps the policy from turning where a turn is needed, which we call behavioral inertia. We propose MOON, a framework that equips a frozen VLN policy with two lightweight modules, adding less than 1% of its parameters. A deviation judge decides when to forget, raising an alarm that clears the history when it predicts that the agent is off route. A recovery policy, trained with GRPO from alarm states, learns how to move on, turning more of the successes found only by sampling into a single greedy rollout. Experiments on R2R-CE and RxR-CE show that MOON reaches the highest R2R-CE success rate among the compared methods and raises the success rate of its frozen base by 5.2 and 6.0 points, and an ablation with a random trigger indicates that this gain depends on when the history is cleared. Without retraining, MOON also improves zero-shot object-goal navigation on HM3D-OVON. Together, these results suggest that deviation recovery depends on knowing when to forget, not only how to act. Code is available at this https URL.
https://arxiv.org/abs/2610.33546
Text-to-3D solid retrieval requires aligning natural language with precise geometry despite variations in pose, scale, and recording conventions. Existing methods discretize Boundary Representation (B-rep) models into point clouds or meshes, or learn features from faces, edges, and topology, risking information loss or lacking explicit invariance guarantees. We propose a text-to-B-rep retrieval framework based on group actions and spectral geometric invariants, making invariance an explicit constraint on descriptor construction. Specifically, we use group actions to characterize equivalence transformations induced by translation, rotation, reflection, uniform scaling, and contour recording conventions. For sketch-extrusion solids, we construct a fixed 280-dimensional spectral geometric descriptor by integrating geometric information from three complementary levels, including cross-sectional regions, contour boundaries, and extrusion structures. Furthermore, we use descriptor-consistent multi-positive sets and geometric attribute supervision to promote structural alignment between text and solids. On Text-to-3D solid retrieval, our method achieves 88.6% Recall@5, exceeding the previous state of the art by 13.6 percentage points and demonstrating the effectiveness of explicit geometric invariants for precise 3D solid retrieval.
https://arxiv.org/abs/2610.33484
We present MOTIO, an agentic skill-engineering system that turns ordinary human-action videos, reality-grounded 3D assets, motion references, and reusable robot skills into executable humanoid loco-manipulation programs. Through in-context task and contact reasoning, an agent constructs staged robot-native interactions and improves them using physics execution, multi-frame feedback, and human validation---without task-specific teleoperation or robot demonstration collection. Agentic 3D supplies metric product and environment assets, while existing whole-body, inverse-kinematics, and dexterous-hand interfaces realize the programs. Across 33 timestamped first approvals, the median recorded agent-turn time is 97.0 minutes and request-to-approval duration is 2.80 hours. Simulation-side layout and object variation prepare a long-horizon bottle-disposal skill for a continuous 101.75-second physical G1 execution in a scanned office; physical refinement reduces screw-tightening thread residual by 76.0%. Agent-generated skills additionally supervise BC/DAgger distillation into one shared reference policy, completing 18 simulated tasks under the same checkpoint without inference-time expert intervention. Project page: this https URL
https://arxiv.org/abs/2610.33446
Real-world environments undergo continual semi-static changes, requiring a memory representation that captures both the spatial and temporal evolution of a scene. Existing spatio-temporal memories for robots typically rely either on structured representations, which are limited to the entities and attributes captured during construction, or on image-based memories, which are constrained to previously observed viewpoints. We introduce GEMS, a framework that combines a persistent spatio-temporal 3D Gaussian Splatting (3DGS) map with an agentic reasoning pipeline. The 3DGS map is reconstructed once and subsequently updated only in regions where the scene changes, storing only these modifications while preserving visual detail across time. The agentic pipeline leverages this map to render novel views on demand, iteratively accumulating evidence to answer spatio-temporal questions and ground objects from natural-language queries. To advance future research, we introduce GEMS-Bench, a spatiotemporal question-answering benchmark focused on semi-static environments. It comprises 3 real-world and 12 synthetic environments, spanning 473 question-answer pairs. We evaluate GEMS on novel-view synthesis quality across scene updates, 3D object grounding, spatiotemporal question answering, and storage efficiency. GEMS outperforms recent baselines in 3D object grounding and spatiotemporal question answering, while achieving rendering quality on par with dedicated scene-update methods. Code and data: this https URL
https://arxiv.org/abs/2610.33158
Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning, but precise spatial grounding remains difficult. Visual generative models offer rich priors over plausible arrangements, yet their outputs require geometric reasoning to become physically valid 3D scenes. We introduce SceneBloom, an agentic framework that combines visual layout sampling with contract-guided 3D compilation. A hierarchical sampler uses diffusion priors to generate furniture arrangements within functional zones. A compiler then uses relations extracted from each proposal to guide geometric fitting and local pose correction. Across five room types, SceneBloom attains the highest visual quality and physical stability among the compared methods and is the only method with no detected mesh collisions and out-of-bounds objects. Its layouts are also closer to the distribution of real rooms than those of all compared baselines. Object navigation policies trained in these realistic scenes achieve a higher success rate in held-out real scans than those trained on an equal number of real training scans. Code is available at this https URL.
https://arxiv.org/abs/2610.32978
In medical robotics, data-driven soft-tissue shape control requires deforming tissue toward desired morphologies through sequential physical interactions. This challenge is particularly important in microscale manipulation, where localized deformation is difficult to observe, represent, and control, while physics-based models can be computationally expensive and difficult to adapt to realistic environments. Optical coherence tomography (OCT) provides high-resolution volumetric perception of tissue deformation, but target-conditioned control requires effective representations of both observed and desired tissue states. In this work, we introduce an OCT-guided data-driven framework for tissue shape control, learned from user-guided demonstrations and executed with closed-loop OCT feedback. We study full-volume, tissue-masked sparse-volume, and voxelized point-cloud representations, with or without residual conditioning, using deterministic (Explicit) and generative diffusion (Diffusion) policies. Across 12 configurations and 576 phantom rollouts on 3-DoF depth and 6-DoF directional tasks, OCT-derived 3D representations support both Explicit and Diffusion policies, with performance depending on representation and residual conditioning. Residual conditioning reduces directional Shape RMSE from 0.748 to 0.555 mm for full-volume Diffusion, while voxelized point-cloud Explicit with residuals achieves 0.534 mm for depth and 0.443 mm for directional control, with comparable accuracy at intermediate unseen targets and consistent performance across deployments. We further evaluate the framework in 60 ex vivo porcine rollouts, extending to biological tissue with final geometric errors comparable to human demonstrations. These results establish volumetric OCT as current and goal representations for learned closed-loop tissue shape control across deterministic and generative action models.
https://arxiv.org/abs/2610.32961
Real-world 3D reconstruction pipelines often rely on multi-view images degraded by lossy compression. While compression artifacts have been extensively studied in single-image or video restoration, their impact on multi-view geometry remains largely overlooked. In this work, we identify compression-induced cross-view geometric inconsistency as a critical failure mode, where view-dependent artifacts disrupt feature matching, dense correspondence, camera parameter estimation, and downstream 3D reconstruction tasks such as novel view synthesis. To address this problem, we propose CompMVR, a compression-aware multi-view diffusion restoration framework that jointly refines compressed views while preserving cross-view consistency, and construct compressed datasets for systematic evaluation. Unlike conventional restoration methods that optimize each image independently for 2D perceptual quality, CompMVR leverages learned compression priors and cross-view correspondence to recover visual details while improving geometric reliability across views. Experiments across diverse datasets, codecs, and compression levels demonstrate gains in restoration quality and downstream 3D tasks, including novel-view synthesis, camera pose estimation, and view matching. These results establish compressed multi-view restoration as a distinct problem and highlight its importance for 3D reconstruction under lossy compression. Code and data for this paper are available at this https URL.
https://arxiv.org/abs/2610.32800
Generating editable 3D urban scenes from a single image requires detailed building assets with a coherent spatial arrangement. Occlusion and perspective ambiguity make it difficult to infer complete building geometry together with consistent relative scales and positions. We present CityLift, a framework that generates individual textured building meshes from an urban image by coupling scene-level spatial modeling with building-level synthesis. CityLift first learns building shape and placement jointly through coupled scene and instance streams, producing coarse sparse structures in a common coordinate system. We then introduce generative spatial inheritance, which maps each building's coarse occupancy and scene-conditioned 3D feature field into a local volume to guide a flow model that generates finer structure. The same coordinate mapping places the generated meshes back into the scene, preserving their spatial relationship to the scaffold. To address the scarcity of urban data pairing scene images with individual 3D buildings, we construct CityLift-5K, comprising 4,997 synthetic scenes with instance masks, building meshes, and placement annotations. Experiments on CityLift-5K and scene blocks from UrbanScene3D and InstanceBuilding demonstrate improved building geometry and scene composition. The project page is available at this https URL.
https://arxiv.org/abs/2610.32728
Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined rotation, translation, and radius variation from arbitrary initial azimuths. Such viewpoint changes also reveal character regions unseen in the initial frame, causing geometric distortions, appearance degradation, and identity drift. To systematically study these coupled challenges, we introduce CLACT, a large-scale Character-centric dataset and benchmark covering diverse Large-Angle Camera Trajectories, with accurate camera geometry and multi-view character observations for training and evaluation. We further propose WorldCast, a framework for world-consistent character video generation under diverse large-angle camera motions. Specifically, we back-project the initial frame into a 3D point cloud using estimated depth, align the point-cloud scale with the target camera trajectory, and render it along the trajectory to obtain explicit geometric guidance and coverage masks. To complement the incomplete character information, we introduce Geometry-Aligned Memory Attention (GAMA). Using relative camera poses estimated jointly from the initial frame and multi-view character anchors, we express anchor and target-view geometry in a common coordinate frame. GAMA uses this geometric alignment to guide the retrieval and injection of view-relevant character features during generation. Evaluations across diverse large-angle camera trajectories demonstrate accurate trajectory following while preserving character geometry, appearance, and identity.
https://arxiv.org/abs/2610.33135
We introduce SemGeo-Gen, an unsupervised method for generating approximate cross-instance semantic-geometric supervision from weakly aligned 3D object collections. Our goal is not to recover exact point-level correspondences, which are often ambiguous across different instances and would require expensive, impractical manual supervision at scale. Instead, we automatically produce approximate correspondences that are semantically meaningful, geometrically consistent, and diverse enough to train modern correspondence models. Given only coarse category-level rotation alignment, SemGeo-Gen lifts multi-view DINOv2 features to 3D, aligns object instances using continuous piecewise-affine registration, and prunes candidate matches using semantic consistency. The resulting 3D correspondences can be projected into rendered views, yielding scalable 3D-3D, 3D-2D, and 2D-2D supervision without manual annotation. We validate the generated correspondences against sparse human annotations from KeypointNet, obtaining 93% PCK@0.10 and 97% PCK@0.15. More importantly, we show that using the generated correspondences for synthetic pretraining improves recent state-of-the-art semantic correspondence models on SPair-71k after fine-tuning on real data, with gains of up to 5 PCK@0.10 points. Together, these results indicate that approximate semantic-geometric supervision generated from 3D assets can improve real-image correspondence learning and serve as a scalable alternative to costly manual annotation. Project page: this https URL.
https://arxiv.org/abs/2610.32663
Continual Wi-Fi sensing must balance plasticity, learning new rooms or users, against stability, keeping earlier ones, yet nodes often cannot retain channel state information (CSI) for privacy and storage reasons. We propose WiMoT (Wi-Fi Moment Transport), which stores the per-class feature mean and covariance of every earlier domain instead of samples. When the representation changes, stored statistics become stale. WiMoT restricts the change to an affine map on a frozen feature basis and applies the same map to the statistics, so they stay valid without old samples. Supervised contrastive learning learns the new domain, a closed-form loss on the stored statistics keeps earlier classes separable, and a Gaussian discriminant classifier, refitted from the transported statistics with equal weight per domain, predicts without domain identity. On 3DO, WiMANS, and Widar3.0, WiMoT's average final accuracies are 94.02%, 89.61%, and 95.16% with at most 0.58 percentage points (pp) of forgetting. On 3DO and Widar3.0, it also has the highest balance of new- and earlier-domain accuracy and is 3.77 and 13.11 pp ahead of the strongest of 21 baselines, which uses replay, staying ahead across domain orders and label budgets. On WiMANS, it matches the strongest replay baseline in accuracy (+0.41 pp) while reducing forgetting from 2.78 to 0.00 pp, and has the highest six-order average accuracy. Because full covariances dominate the memory, storing them as rank-32 factors shrinks the moment memory to 6.4%, losing at most 0.49 pp of accuracy, within edge-node storage budgets.
https://arxiv.org/abs/2610.32660