Monocular occupancy prediction in indoor scenes aims to recover a scene's 3D geometry and semantics from a single RGB image. Existing methods are restricted to a closed set of predefined categories, limiting their ability to generalize to unseen categories. This limitation is particularly critical in indoor scenes, where objects exhibit highly diverse and fine-grained semantic categories. We study open-vocabulary monocular occupancy prediction for indoor scenes and present OVM-Occ, a Gaussian-based occupancy framework with an instance-aware vision-language teacher. Specifically, we adopt Language-Embedded Gaussians as the intermediate scene representation, propose a geometry-aware deformable attention module to refine Gaussian semantic features, and construct instance-level vision-language embeddings to provide reliable semantic supervision. We further introduce geometry-aware decoupled semantic distillation to mitigate the interference between geometry learning and semantic learning. To evaluate open-vocabulary occupancy prediction performance, we introduce OpenOcc-ScanNet and OpenOcc-Replica, two extended benchmarks with more diverse and fine-grained semantic categories. Experiments show that our method achieves state-of-the-art performance in open-vocabulary monocular occupancy prediction for indoor scenes, outperforming the previous state-of-the-art approach by 12.2 mIoU and 0.6 IoU on the Occ-ScanNet dataset, with consistent gains under new open-vocabulary evaluation protocols.
https://arxiv.org/abs/2610.35312
Optical coherence tomography (OCT) is a non-invasive imaging modality used for visualization of retinal tissue. However, OCT volumes are affected by speckle noise, which degrades image contrast and obscures fine structural details. Furthermore, modern clinical practice requires large field-of-view, high-resolution OCT volumes, whose storage and transmission are demanding for archiving and teleophthalmology applications. To address aforementioned challenges, we propose a low-rank multi-scale entanglement renormalization ansatz (MERA) tensor network approximation of 3D OCT image volume, where the image volume is represented as contractions of a top core factor encoding global features and multiple interacting low-rank orthogonal or semi-orthogonal factors modeling inter- and intra-B scan correlations. This representation jointly enables compression, denoising, and feature extraction. Unlike deep learning approaches, the proposed approach is training-free and processes each OCT volume independently. We evaluate the proposed framework on OCT image volumes acquired by two different scanners and demonstrate improved visual quality and reduced retinal layer segmentation errors in comparison with several competing methods. We also extract MERA features from two clinical OCT volume datasets. They are subsequently classified using a Grassmann-manifold nearest-subspace classifier. With the subspace dimension as its only hyperparameter, the classifier is theoretically shown to be robust in small-sample clinical scenario. We demonstrate competitive accuracy of classification of retinal diseases in these small-sample settings, where deep learning methods are often limited by the scarcity of labeled data. The proposed structure-aware model-driven representation learning for high-dimensional data under limited supervision provides good generalization performance while maintaining high interpretability.
https://arxiv.org/abs/2610.35271
We present GaussianSpline, a dynamic 4D Gaussian Splatting method that models per-Gaussian motion using adaptive, non-uniform piecewise cubic Bézier splines. Unlike approaches based on global deformations, fixed-order polynomials, or uniformly parameterized splines, GaussianSpline jointly learns the Bézier control points and the temporal partition of each Gaussian's trajectory. This adaptive representation allocates greater temporal capacity to highly dynamic regions while maintaining compact trajectories for near-static regions, enabling high-fidelity reconstruction of complex and rapidly changing motion. To jointly achieve globally smooth motion and local adaptivity, we enforce $G^1$ continuity between consecutive Bézier segments using a reflection-based constraint on their control points. This produces smooth, fully differentiable trajectories while preserving the flexibility of non-uniform temporal parameterization. Experiments on the Neural 3D Video benchmark, the Google Immersive dataset, as well as on synthetic scenes demonstrate that GaussianSpline substantially improves reconstruction quality in scenes with highly non-uniform and challenging dynamics, while maintaining competitive performance on general dynamic scenes compared with state-of-the-art 4D Gaussian Splatting methods.
https://arxiv.org/abs/2610.35224
Game development stresses coding agents in ways general software engineering does not: correctness depends on how engine APIs, serialized scene state, and runtime behavior interact, not on source code alone. Existing benchmarks mainly target platforms such as Godot and heavily rely on LLM judges or coarse task-level outcomes. We present UnityBench-Mini3D, a benchmark of 77 project-level Unity tasks organized around seven expert-defined skill categories rather than tutorials or genres, with three difficulty tiers. Each task pairs a complete Unity project with natural-language requirements and is evaluated using 1,178 held-out, human-authored milestone tests covering scene structure, component configuration, and runtime behavior. This in-engine evaluation provides deterministic partial credit, localizes failures, and distinguishes partial implementations from complete solutions without relying on subjective judges. Across 21 models and 9 coding harnesses, the average pass rate reaches 80.9% on easy tasks but falls to 35.2% on hard tasks, with just 57.7% overall. UnityBench-Mini3D provides a reproducible, diagnostic testbed distinguishing systems across difficulty levels.
https://arxiv.org/abs/2610.35980
A cooperative 3D detector can miss a vehicle even when the LiDAR points on it remain unchanged. We study this failure under adverse weather as Weather-Induced Context Interference. To our knowledge, this is the first controlled study of how weather-related exterior changes remove cooperative benefits while preserving all points inside annotated objects. Controlled experiments on simulated and real roadside inputs show that exterior loss changes object representations before fusion and removes previously useful assistance. On real inputs, restoring object-neighborhood features recovers 30 of 31 induced failures; three equal-area exterior controls recover none. The failure condition also appears with a second fusion model. These findings motivate Adverse-Weather Cooperative Repair (AWCR), with separate implementations for the available supervision. Point Classifier filters added weather returns in simulation. On real inputs, Local Correction refines candidates and Quality Selection checks them against current measurements, without naturally paired clear/adverse-weather recordings. Candidate tracing shows that correction supplies accurate geometry for some targets that original candidates cannot localize at the evaluation threshold. On natural adverse-weather CoInfra development data, AWCR improves car bird's-eye-view (BEV) AP@0.7 by 4.66 points with V2X-ViT and 5.56 with AttFuse. On simulated V2X-R fog, it improves vehicle BEV AP@0.7 by 4.47 points at a fixed 4,096-candidate budget.
https://arxiv.org/abs/2610.35110
Blendshape generation for 3D models has been extensively researched, but very few works address generating blendshapes for models with multiple disconnected parts. We present a case study of generating fixed facial expression blendshapes for commercial anime-style 3D character models with up to 11 parts per face. To make sure that our system can handle models in a way that is agnostic to topology, we train neural networks to generate deformation fields around the input meshes. We employ at least one network to independently process each part, and the relative positions of their outputs are coordinated by having each network also process the geometry of an anchor part. We use two mechanisms to improve accuracy: having the networks predict whether the output displacement is zero or not, and classifying blendshapes into different size groups and dedicating a network to each group. We also introduce a method to improve blendshape quality by enhancing bilateral symmetry. Our method is simpler than recent neural-network-based works and solves a real problem of the user community of these models.
https://arxiv.org/abs/2610.35076
Vision-language navigation (VLN) requires an embodied agent to follow language instructions through 3D environments. Maintaining persistent episodic memory remains a challenge for VLM-based streaming agents in long-horizon navigation. We present MEMVLN, a streaming episodic memory framework that maintains a bounded bank of compressed perceptual features annotated with timesteps and action-derived relative poses, and produces compact memory tokens via cross-attention. We pair the proposed memory with a frozen pretrained geometry encoder. To learn the memory module, we design a masking-based trajectory summarization task with multi-granularity sub-trajectory decomposition, encouraging route reconstruction exclusively from episodic memory. Under navigation training restricted to the official R2R/RxR trajectories, MEMVLN achieves state-of-the-art performance on most reported metrics on standard VLN-CE benchmarks. Long-horizon analyses further characterize when episodic memory is useful. For physical evaluation, we collect 30 instruction-conditioned episodes in one physical scene, use 24 as demonstrations for post-training, and hold out six for testing. On the held-out episodes, MEMVLN improves success over the VLM baseline from 17% to 40%, and post-training further raises it to 47%.
https://arxiv.org/abs/2610.35066
Estimating forces acting on Deformable Linear Objects (DLOs) is challenging due to their underactuated nature. However, reliable contact estimation is crucial to precisely control them and enable safe manipulation tasks. Differently from the various approaches presented in the literature, this work adopts a probabilistic formulation where the DLO state and sensor data are related through conditional distributions. In particular, factor graphs are used to determine the magnitude, direction, and location of a 3D force acting on a DLO, while simultaneously reconstructing its shape. Since DLOs are not actuated and are typically thin, like cables and wires, strain gauges and actuation readings are usually impractical. Therefore, to overcome this issue, this work is tested using one type of sensing information only, thus developing a generic technique suited for a wider variety of tasks. Realistic tests are performed by introducing noise into the measurements while the DLO follows a prescribed path in the presence of external forces that are accurately estimated.
https://arxiv.org/abs/2610.35058
Camera-based bird's-eye view (BEV) perception methods such as Fast-BEV have demonstrated promising results with fast inference speed and competitive accuracy. However, their robustness to real-world corruptions remains insufficiently explored, posing risks for autonomous driving deployment where environmental variations are inevitable. In this paper, we propose Sparse Recovery Bird's-Eye View Model Soup (SR-BEVS), a sparse recovery learning approach that simultaneously improves clean accuracy and corruption robustness without requiring additional data or architectural modifications. Our method identifies pruning candidates based on layer-wise weight magnitudes, applies random pruning to create diverse sparse models, and retrains each model with a randomly sampled learning rate. By averaging these diverse recovered models into a single dense model, we achieve enhanced robustness against various corruptions while introducing zero inference overhead. We further provide a mode connectivity analysis demonstrating that our pruning-based diversification preserves the connected low-loss basin necessary for stable weight averaging. Experiments on the nuScenes dataset demonstrate up to 33.8% improvement in corruption robustness and a 1.8% gain in clean accuracy over the Fast-BEV baseline, with consistent improvements across sensor noise, weather distortions, and illumination changes. Our simple yet effective approach may be applicable to other BEV models.
https://arxiv.org/abs/2610.34976
Grasping is a foundational capability in robotic manipulation. Scene-level 6-DoF grasp synthesis relies on point clouds for metric geometry, yet real-world point observations are often noisy, incomplete, and over-smoothed. RGB images provide object-region, boundary, and appearance cues, yet two bottlenecks limit their effective use in scene representation and local grasp reasoning. We present MMGNet, a Multi-Modal Grasp Synthesis Network that addresses these bottlenecks through hierarchical image-to-3D feature injection and rotational graspness modeling. Hierarchical injection integrates multi-scale image features throughout 3D representation formation, while the rotational graspness jointly predicts the grasp approach direction and in-plane rotation before organizing local image-informed features through grasp-shaded grouping. Ablation studies show that these two modules provide complementary gains. MMGNet achieves a mean AP of 60.34 on GraspNet-1Billion with RealSense, surpassing all compared methods. In real-world experiments with adversarial grasp objects, MMGNet improves the grasp success rate over AnyGrasp by 8.46 percentage points. \emph{Code, models, and data will be released upon publication.}
https://arxiv.org/abs/2610.34893
When zooming between dual cameras on smartphones, prominent discontinuities in both geometric perspective and color rendition inevitably degrade the visual experience of users. To address this issue, we introduce the dual-camera smooth zoom (DCSZ) task, aiming to synthesize continuous intermediate frames for fluid zooming. However, directly applying existing video frame interpolation (VFI) models to this task is severely hindered by substantial domain gaps and the practical intractability of capturing real-world continuous ground-truth. To this end, we propose a novel data synthesis framework to generate high-fidelity DCSZ training sequences, named ZoomGS v2. It explicitly decouples geometric and color transformations from 3D scene representation modeling, thereby enabling extensive data generation from easily accessible single-camera 3D scenes. Furthermore, we develop ZoomFI, a specialized VFI network tailored to the DCSZ task, which leverages complementary bidirectional warping for comprehensive dual-camera information fusion. Extensive experiments on test datasets captured using two mobile phones demonstrate that training with the constructed DCSZ data significantly improves the performance of various VFI models. Moreover, ZoomFI achieves state-of-the-art results in both quantitative metrics and visual quality. The datasets, code, and pretrained models are available at this https URL
https://arxiv.org/abs/2610.34854
Recent multi-view Transformers (e.g., DUSt3R and VGGT) have advanced 3D reconstruction by scaling training data and model capacity from two views to many views and long sequences, subsuming the classical SfM/SLAM pipeline of feature extraction, matching, and pose estimation in a single feed-forward pass. Yet this subsumption hides the interfaces between pipeline stages---correspondences, geometry, and pose are entangled in a single forward pass, leaving supervised fine-tuning as the major path to improvement and offering no mechanism to correct predictions from geometric evidence at test time. We propose PosePlaner to close this gap by reviving the classical coupling between correspondences and pose via flow matching, treating pose refinement as a conditional generation problem that takes coarse geometric matches and initial pose as input condition and fuses the resulting pose hypotheses into a single refined estimate, providing a continuous, data-driven analog of RANSAC voting. Our method is trained efficiently on two-view data, yet serves as a periodic refiner for streaming n-view pose estimators with no retraining. Empirically, it corrects failures of feed-forward predictors, substantially improves correspondence-based solvers, and reduces accumulated drift in long streaming sequences.
https://arxiv.org/abs/2610.34845
Diffeomorphisms provide a flexible, topology-preserving mathematical tool for modeling complex spatial or temporal deformations and are used in various scientific fields. However, making these deformations simultaneously highly expressive and computationally efficient remains challenging. Continuous Piecewise-Affine Based (CPAB) transformations (Freifeld et al., ICCV 2015; IEEE TPAMI 2017) offer an attractive solution by parameterizing a family of diffeomorphisms via continuous velocity fields that are piecewise affine with respect to a chosen tessellation of the domain. Importantly, $d=\dim(\theta)$, the dimension of the parameter vector $\theta$, depends on the fineness of the tessellation rather than on the data resolution. Despite this compact parameterization, CPAB optimization has long been hindered by the tight coupling between trajectory integration and gradient computation with respect to $\theta$. We introduce FG-CPAB, a factorized-gradient formulation for scalable CPAB transformations. By separating integration from parameter-space projection, our method reduces gradient computation complexity from $\mathcal{O}(dTN)$ to $\mathcal{O}(TN+dC)$, where $T$ is the number of integration steps, $N$ is the number of transformed points, and $C$ is the number of tessellation cells. This reformulation yields speedups of up to four orders of magnitude (e.g., $\approx 10^4\times$ in 2D), substantial memory savings (e.g., $\approx 500\times$ reduction in peak GPU memory usage in 2D), and dramatically higher expressiveness. This makes fine-tessellation CPAB practical in 2D and 3D for the first time, enabling highly expressive parametric diffeomorphisms.
https://arxiv.org/abs/2610.34766
Visual captures provide detailed scene appearance, but converting them into interactive simulation environments requires object reconstruction, physical modeling, and correction of intermediate errors. We present SceneAgent, an agentic pipeline that coordinates these steps through simulator-based visual inspection and repair. The pipeline processes 3D Gaussian Splatting (3DGS), photogrammetry, LiDAR captures, AI-generated 3DGS scenes, and 4D videos of dynamic scenes, and combines object segmentation, physical parameter estimation, part decomposition, articulation, and deformable simulation. To support policy learning, SceneAgent generates diverse object variants ("digital sisters") and scripted demonstrations. On a cluttered bin scene from GraspClutter6D, SceneAgent raises F1 at 1 cm for every coding agent with scorable outputs both with and without its skills, and its reconstructions are better than SimFoundry: all agent configurations exceed SimFoundry's F1 score, with a best of 60.75% versus 6.9%. On three dynamic scenes from 4DCodeBench, SceneAgent raises the mean dynamic IoU of Gemini 4 Argon from 0.86% to 99.09%. We further demonstrate diverse simulated interactions and preliminary policy transfer to a real robot.
https://arxiv.org/abs/2610.34745
Learning high-level causal variables from low-level observations is a central problem for artificial intelligence. With known node semantics but an unknown graph, visual readout errors can misalign model settings with environment intervention values. We address this mismatch by pairing image readouts with verified values attained through fixed round-robin interventions. With encoder and decoder frozen, a dimension-wise invertible calibration map puts visual responses and target settings in shared numerical units. After freezing this map, the agent selects interventions to resolve graph directions and fits local mechanisms to predict consequences; inverse calibration returns counterfactual states to the decoder's original coordinates. Across Domino, Pick-and-Place, Balance, Gears, CAUSAL3D, and CausalWorld, we evaluate graph discovery, intervention consequences, and counterfactual images. Controlled domino experiments show that interventions resolve orientation ambiguity left by equal additional observations. In a matched-data domino control, calibration reduces the mean error of predicted changes in other variables within the same factual context, relative to an uncalibrated model.
https://arxiv.org/abs/2610.34711
Driving video captured through a windshield violates the world-space consistency assumed by 3D Gaussian Splatting (3DGS): the road scene exhibits parallax while cabin reflections remain attached to the camera, causing standard 3DGS to embed reflected content into the reconstructed scene. We introduce RIDE-Splat, a pipeline for reflection-free 3D reconstruction from posed driving video without clean images, reflection masks, or pretrained networks. RIDE-Splat assigns world-consistent transmission through the windshield to a 3DGS scene and the dominant camera-attached reflection to one shared, signed RGB image. It builds the clean reconstruction in two passes. First, it learns the 3D geometry and the signed reflection image, representing both added radiance and transmission attenuation. Then, it uses the reflection-removed training images to fit a clean 3DGS model. At inference, the reflection image is discarded, preserving the standard 3DGS rendering path. We also introduce the RIDE-Splat Dataset, the first 3D reconstruction benchmark for reflection removal from driving video -- with real driving scenes, physical windshield reflections in training views, and separately captured non-reflective evaluation images. Across the RIDE-Splat Dataset, XLD, and Wayve, RIDE-Splat outperforms 3DGS, DC-Gaussian, and RobustSplat on all nine aggregate metrics, improving PSNR by up to 3.59 dB and reducing LPIPS by up to 0.0876. We achieve the highest metrics in 38 out of 42 per-scene comparisons and removes windshield reflections that remain visible in the baselines while preserving the transmitted scene.
https://arxiv.org/abs/2610.34632
Erasing all furniture from a single room image to generate its empty counterpart is valuable for XR applications such as diminished reality and virtual staging. The challenge is twofold: inpainting the furniture regions with realistic content, and doing so without distorting the room's 3D geometry. Prompt-driven image editors, such as FLUX.2, handle realism impressively, but their structural faithfulness is inferior to explicit layout conditioned inpainting. To improve geometric consistency, we propose a training recipe for finetuning a LoRA on 2,500 furnished-empty room pairs. FLUX.2 with our LoRA adaptor significantly improves geometric consistency while retaining the high texture fidelity. This single-photo inpainter can be an effective building block for depth-aware and 3D-consistent XR pipelines.
https://arxiv.org/abs/2610.34597
Robots that follow natural-language instructions unlock a wide range of autonomous applications in households, warehouses, and labs. Real-world environments are diverse and often heavily cluttered, requiring robots to plan over multiple steps, act, and replan as they work toward a goal. We present CLARO (CLutter-Aware Robot Orchestrator), a VLM agent that orchestrates a set of perception and manipulation skills: open-vocabulary object detection, segmentation, 6-DoF grasping, and non-prehensile pushing to locate and retrieve a language-specified target in clutter. CLARO maintains a memory of its past actions to support long-horizon execution, and emits manipulation targets (grasp poses/3D waypoints) allowing transfer across robot arms without task-specific training. We evaluate CLARO against a range of methods on a dynamic simulation environment and standard image-based benchmarks, demonstrating strong generalization across object classes, lighting, and clutter levels. CLARO attains an average success rate of 89.1%, a relative improvement of over 16% on the strongest competing method in high cluttered scenes. We further analyze performance along grounding and grasping axes to characterize where each method succeeds and fails. Finally, we deploy CLARO on a robot arm across diverse cluttered scenes, achieving a success rate of 88.8%, and demonstrating strong sim2real generalizability.
https://arxiv.org/abs/2610.24016
Humans often solve spatial problems by mentally simulating visual transformations. In contrast, conventional vision-language models (VLMs) reason primarily through language. We investigate whether VLMs can solve spatial problems by reasoning with both text and generated visual states. To this end, we introduce WM-VLM, which equips a pretrained VLM with a lightweight world model branch for generating intermediate visual states. Our two-stage training first teaches the model to generate the next visual state and then to use that state for reasoning. We programmatically construct spatial reasoning tasks with verifiable intermediate visual states. These tasks allow us to evaluate how well the model generates visual states and how much it relies on them to answer the question. On 2D and 3D mental rotation tasks, WM-VLM consistently outperforms the supervised fine-tuned backbone, with gains of up to 39.25 percentage points. Ablations suggest that these gains depend on the generated visual states, as removing or corrupting them sharply reduces performance. Together, these results suggest that internal world models offer a promising path toward VLMs that reason in both language and visual space. Code is publicly available at: this https URL
https://arxiv.org/abs/2609.34826
Background/Objectives: Rapid differentiation of ischemic and hemorrhagic stroke subtypes is vital for acute management. Although current deep learning models achieve high single-dataset accuracy, they suffer from "shortcut learning" and domain shift in external validation. This study proposes a hierarchical computer-aided diagnostic (CAD) system mimicking emergency triage. Methods: We introduce a 3-channel Radiology-Focused Preprocessing pipeline that feeds radiological Hounsfield Unit (HU) windows into Convolutional Neural Network (CNN) and Vision Transformer (ViT) backbones via asymmetric formats (.mat and .png). The architecture utilizes a novel joint cross-attention fusion network optimized by an Integrated Orthogonal-Focal Loss. Results: Our system achieved a 95.48% F1-score on the internal stroke dataset. However, multi-center external validation (AISD, BHSD, PhysioNet) using a Mask Anchor filter revealed a drop to the 58-62% range, exposing the "internal validation illusion" caused by hardware noise. Critically, models exhibited high precision (77%) but low sensitivity (57%) for ischemic stroke, proving prone to hemorrhage overdiagnosis. Multi-seed variance analysis demonstrated that the DenseNet201+ViT backbone yielded the lowest deviation (0.59) and highest stability, making it the most reliable architecture for real-world clinical integration. Conclusions: To overcome diagnostic challenges, future research must focus on multimodal architectures that combine 3D volumetric extraction with clinical data.
https://arxiv.org/abs/2610.34529