Significant advancements in 3D asset creation have enabled high-fidelity 3D generation from images. However, most existing representations remain inherently static, lacking the ability to model physically plausible behaviors under dynamic interactions. We present \textbf{PhysCreator}, a unified framework that directly generates simulation-ready 3D representations with spatially varying physical properties from images. Unlike prior approaches that treat physical attributes as simple post-hoc predictions or rely on expensive per-instance optimization, we reformulate physical property estimation within a unified 3D representation learning framework. We introduce a voxel-aligned latent space by lifting image observations into a spatially structured 3D representation, in which geometry, appearance, and physical properties are jointly modeled and inferred in a feed-forward manner. To enable scalable learning without densely annotated physical ground truth, we leverage vision-language distillation to transfer material-aware semantic priors from powerful vision-language models into spatially grounded voxel-level supervision. Experiments demonstrate that our method achieves superior visual quality, physical plausibility, and generalization compared to prior approaches.
https://arxiv.org/abs/2610.34473
Spatial audio authoring coordinates source decisions with soundfield synthesis. For editing, plans specify what to change and retain, while reference audio supplies further acoustic detail. We present AMBIT, a unified framework for native First-Order Ambisonics (FOA) generation and editing with three connected contributions. First, a shared Transfusion backbone couples autoregressive planning with rectified-flow rendering through executable ScenePlans that specify source content, activity, and 3D trajectories. For editing, the plan describes the full target scene, including retained sources; contrastive features ground the requested change, while full reference latents supply residual acoustic detail for preservation. Second, an FOA-aware continuous VAE combines shared-decoder omnidirectional recovery, asymmetric grouped KL, and spatial covariance matching to preserve content and inter-channel structure. Third, joint Transfusion on-policy self-distillation (OPSD) refines planning on student-generated prefixes and rendering at sampling states reached under student plans, with target-conditioned teachers supervising both modes of the shared student. Evaluations across speech, music, and sound show improved generation content and spatial quality, acoustic fidelity during instruction-guided editing, and unedited-source preservation over the compared baselines. Project page: this https URL
https://arxiv.org/abs/2610.34415
Non-rigid structure from motion (NRSfM) aims to recover camera motion and time-varying 3D shape from tracked 2D image measurements. Recent high-performing methods show that shape-space factorization remains highly effective for this task. These methods often use costly solvers for two key steps. First, a semidefinite programming (SDP) cone solver to perform Euclidean correction. Next, an alternating direction method of multipliers (ADMM) solver to recover the low-rank shape. These steps often scale poorly to long sequences and dense point tracks. We propose a fast, scalable NRSfM solver that avoids these costly steps. For rotation estimation, we introduce a differentiable Euclidean correction that directly optimizes small factors for each sequence. A row-polar projection then maps each estimated camera block to the closest row-orthonormal matrix. For shape estimation, we introduce an unrolled spectral-proximal solver. It combines reprojection-gradient steps with weighted singular-value shrinkage in the reshuffled shape domain. This solver further uses FISTA-style restart and continuation. The spectral shrinkage operator itself is classical, but we embed it in a fixed differentiable solver, while preserving NRSfM's geometric constraints. The proposed approach is category-agnostic, requires no external training data, and maps naturally to modern accelerator-friendly linear algebra primitives. Across sparse, dense, noisy, missing-data, and long-sequence benchmarks, our solver achieves substantial speedups with competitive reconstruction accuracy, including 7x-1000x runtime improvements on dense sequences with 28,887 tracked points.
https://arxiv.org/abs/2610.34403
Scaling vision-language-action (VLA) models is constrained by scarce action-labeled demonstrations and incompatible control spaces across robot embodiments. We present RynnVLA-Latent, a framework that turns heterogeneous interaction videos into scalable supervision for robot policy pretraining. At its core, RynnLAM learns continuous, 3D-grounded latent actions from visual transitions without requiring native robot controls. By combining residual future-feature prediction, camera-compensated 3D-flow supervision, and camera-motion decoupling, RynnLAM encourages representations that capture control-relevant motion rather than appearance changes alone. We apply RynnLAM to 30.1K hours of human, robot, and simulation videos, producing 745.52M latent-action descriptors. RynnVLA-Latent then learns to predict latent-action chunks from visual observations and language through flow matching, before adapting its pretrained backbone and action expert to embodiment-specific robot actions. The resulting 4B policy achieves 98.8% success on LIBERO, 84.7% on LIBERO-Plus without benchmark-specific adaptation, 51.9% average success across five VLABench tracks, and 88.6% average success on the RoboTwin 2.0 bimanual benchmark. It also achieves the highest observed success rates among the compared methods on six real-world manipulation tasks across dexterous-hand and mobile-gripper platforms. Together with representation ablations and data-scaling results, these findings demonstrate the potential of latent-action supervision for scaling robot policy learning beyond native action-labeled data.
https://arxiv.org/abs/2610.34356
3D Gaussian Splatting (3DGS) has become a standard representation for real-time novel-view synthesis. Yet, its quality-efficiency trade-off still relies heavily on adaptive density control. Existing cloning, splitting, and pruning rules use proxy signals, such as position gradients, opacity, and image-space error. Although effective in practice, these signals do not directly answer the structural question behind density control: where should new Gaussians be allocated to reduce the multi-view reconstruction loss, and which existing primitives can be pruned with minimal penalty. To address this, we propose first-variation birth-death control for 3DGS, a principled approach that replaces heuristic structural decisions with a variational score derived from the reconstruction loss. At each structural update, we freeze the current Gaussian population, attach auxiliary mass coordinates to each primitive, and differentiate the multiview loss with respect to these coordinates. We demonstrate that this score is a coordinate of the first variation of the Splat Regression Model, giving a rigorous local descent surrogate for birth-death moves: high-score Gaussians are selected as birth sites, while low-score, low-opacity Gaussians are selected for removal. Across standard 3DGS benchmarks, integrating this score into 3DGS-MCMC yields state-of-the-art reconstruction quality and outperforms existing methods, delivering the most significant gains under tight Gaussian budgets. Ultimately, our work provides compelling evidence that gradient-based variational metrics offer a principled alternative to proxy heuristics in 3DGS.
https://arxiv.org/abs/2610.34344
We propose a novel method for robust point cloud registration with only one tunable parameter. Our method, dubbed TLP, uses truncated $L_p$ functions with different values of $p$ to assign priority scores to correspondences, select the hypothesis, and refine the final model. By leveraging the robustness of truncated functions, TLP effectively handles the high outlier rates commonly encountered in real-world 3D feature matching. We also exploit GPU parallelization to evaluate hypotheses efficiently, enabling registration from thousands of correspondences in under a second on average. With only one tunable parameter, our method offers greater practicality than multi-parameter methods that require dataset-specific tuning of several parameters. Evaluations on public benchmark datasets demonstrate that TLP achieves higher accuracy than state-of-the-art single-parameter methods. Furthermore, it outperforms two widely used multi-parameter methods on three of the four evaluated datasets while maintaining competitive runtime.
https://arxiv.org/abs/2610.34271
3D Gaussian Splatting (3DGS) has emerged as a promising approach for fast, high-quality novel-view rendering. However, its large parameter size remains a bottleneck for storage and transmission. We propose RacerGS, a compact 3DGS compression framework that achieves scene reconstruction at significantly reduced storage sizes with preserved fidelity. To obtain compact and spatially coherent features, we design a hash projection model that projects the anchor hash encodings into compact context features. Additionally, we introduce a FiLM-modulated autoregressive GRU context model that utilizes causal dependencies among anchor feature groups and uses recurrent hidden states to refine entropy-model parameters, improving bitrate efficiency. Furthermore, we adaptively entropy-code quantized anchor-attribute residuals relative to their context-predicted means, leveraging spatial consistency to reduce symbol entropy. Overall, RacerGS achieves more than 150x compression over vanilla 3DGS and 28x over Scaffold-GS, while providing comparable rendering quality. Extensive experiments across five datasets demonstrate that RacerGS outperforms prior 3DGS compression methods in both storage reduction and rate-distortion performance.
https://arxiv.org/abs/2610.34263
Scalable 3D Gaussian Splatting allows one scene representation to serve different Gaussian-count budgets, yet its quality-budget curve may lag behind models optimized separately for each budget. Reducing the number of Gaussians changes both the selected members and the reconstruction tasks carried by the survivors; parameters inherited from a high-budget model may fit a low-budget representation poorly. We propose ParetoGS, which describes member changes and parameter evolution with a small set of adapted budget anchors and decodes intermediate budgets without separate optimization at every requested count. ParetoGS alternates pruning and fixed-member adaptation to build nested anchors with persistent identities, and encodes their parameter changes relative to the full model in a compact residual atlas. At decoding, it interpolates the states of shared members and gradually introduces the rendering contributions of new members, connecting sparse anchors into a continuous-budget representation. Across 13 scenes, ParetoGS attains better average PSNR, SSIM, and LPIPS with fewer Gaussians than the compared prefix methods at 10% of each method's own full model. From a shared full model, it also outperforms FlexGS-imp at its trained 1%, 5%, and 10% budgets and NanoGS-imp at the 1% and 0.1% budgets. On Garden, its non-anchor quality approaches an empirical reference from independently optimized GNS models at higher retention ratios and exceeds it at some lower-budget points. Across 13 scenes, encoding reduces mean additional state from 390.0 to 85.7 MB with an average PSNR change of 0.01 dB. Project page: this https URL
https://arxiv.org/abs/2610.34235
High-resolution 3D Gaussian Splatting training increases pixel and Gaussian-tile intersection counts, expanding rasterization caches that coexist with projection and gradient state at peak memory. A complete-view update aggregates gradients across the view; each region's forward and backward caches can be released after its contribution is collected. BoundedGS separates rasterization and projection backward passes and bounds the active local rasterization working set according to its measured load. Candidate-indexed projection and compact gradient storage address the view-level peaks exposed by this change, while CPU-assisted structure rebuilding and bounded image supply manage resources outside rendering. In a resolution sweep at a fixed count of about 6M Gaussians, the measured rendering working set stays within 1.073-1.077 GiB from 1K to 16K; at 11K, a warm pass takes 19.79 seconds versus 21.76 for full-frame execution. Across five native 5K outdoor scenes, full training reduces the mean rendering working set from 9.97 to 1.76 GiB (82.3%), retains similar reconstruction quality, and shortens training time from 36.7 to 33.9 minutes. Project page: this https URL
https://arxiv.org/abs/2610.34233
Purpose: To compare 2D, 2.5D, and 3D residual networks for pulmonary nodule malignancy-risk classification and evaluate momentum-contrast pretraining, mild augmentation, and exclusion of indeterminate ratings. Methods: A retrospectively prepared LIDC-IDRI cohort contained 2,654 nodules labeled benign, indeterminate, or malignant using median radiologist ratings. Patient-disjoint splits comprised 1,876 training, 382 validation, and 396 test nodules. Representations included one axial slice, five neighboring slices, and a local CT volume. Each track evaluated a randomly initialized baseline, momentum-contrast pretraining followed by fine-tuning, and supervised training with mild augmentation. Checkpoints were selected by validation Macro-F1. The 2D experiments used three seeds; 2.5D and 3D results were single-run estimates. A separate binary experiment excluded indeterminate nodules. Results: Augmented models achieved test Macro-F1 values of $0.6134\pm0.0075$ for 2D, $0.6537$ for 2.5D, and $0.5403$ for 3D; the 2D uncertainty denotes population standard deviation across seeds. Corresponding accuracies were $0.6128$, $0.6869$, and $0.5455$. Augmentation improved Macro-F1 within every track, whereas the tested pretraining recipes reduced it. Binary Macro-F1 values were $0.8227$, $0.8664$, and $0.7554$, respectively. Conclusion: Augmented 2.5D achieved the highest observed performance. Differences in preprocessing, optimization, capacity, and replication limit attribution to dimensionality. Labels reflect radiologist-assessed malignancy risk rather than pathology-confirmed cancer. Code and experimental results are available at this https URL.
https://arxiv.org/abs/2610.35960
While Multimodal Large Language Models (MLLMs) excel at zero-shot reasoning, their spatial capabilities are primarily evaluated through static, passive observation. In complex, human-centric scenes, occlusion often hides crucial geometric evidence, and passive benchmarks force models to guess rather than recognize their own visual uncertainty. To bridge this gap, we introduce SATE-Bench, a novel interactive benchmark comprising 316 real-world scenes and 2,525 multi-turn QA pairs to evaluate visual self-awareness and active exocentric view-exploration. It combines a Passive multi-view control with an Active exploration setting, where models start from a severely occluded view and must iteratively query adjacent viewpoints until they gather enough evidence to fully ``sate'' the question, scored by a step-penalized efficiency reward. Evaluating state-of-the-art MLLMs reveals that they terminate exploration prematurely while reporting high confidence, and struggle with fine-grained 3D geometric tasks; matched-view controls further attribute the Active--Passive gap primarily to insufficient evidence acquisition. Moreover, fine-tuning with Group Relative Policy Optimization (GRPO) shows that rewarding view-seeking increases active exploration but lowers overall accuracy, as models over-explore and fail to fuse expanding multi-view contexts across turns. These findings indicate that scaling passive multi-view perception does not intrinsically yield active spatial reasoning, highlighting the need for models that know where to look, how to integrate what they see, and when to stop. Code and data are available at this https URL
https://arxiv.org/abs/2610.34149
Open-vocabulary 3D occupancy prediction is important for embodied agents operating in complex environments whose semantic categories extend beyond fixed taxonomies. While recent studies have explored open-vocabulary occupancy in outdoor driving scenarios, indoor environments remain challenging due to dense occlusions, complex geometry, and fine-grained long-tailed semantics. To reduce the need for expensive voxel-level semantic annotations, we study a geometry-only supervision setting requiring only binary occupancy labels. We build upon Language-Embedded Gaussians as a unified representation coupling 3D geometry with language-aligned semantics. For geometry learning, we introduce an opacity-aware Poisson-based Gaussian-to-Occupancy formulation that enables stable volumetric aggregation under binary occupancy supervision. For semantic learning, we render Gaussian features into images and align them with a frozen open-vocabulary model, together with Progressive Temperature Decay to reduce feature mixing during Gaussian splatting. Building on this framework, we further introduce Instance-Level Semantic Consistency to alleviate fragmented object predictions, and Covisibility-Aware Support-View Selection to provide informative and less redundant multi-view semantic supervision. We also extend our framework to outdoor driving scenarios to evaluate its generality across substantially different environments. Extensive experiments on indoor and outdoor benchmarks demonstrate that our method achieves strong open-vocabulary occupancy performance, validating the effectiveness and generality of our framework. Code will be available at this https URL.
https://arxiv.org/abs/2610.34093
Building embodied agents that can perceive, reason, and act across diverse 3D worlds is a central research direction toward artificial general intelligence. Yet most existing work remains confined to specific tasks in a single scene and transfers poorly to new environments, leaving general embodied agents for open-world settings under-explored. We refer to such agents as Embodied World Agents (EWAs), whose defining property is the ability to understand diverse visual environments and execute general actions in open-world conditions. To advance EWA research, we study open-world embodied navigation-planning and release EmbodiedWorld-200K, a large-scale dataset of over 200K samples spanning diverse scenes. Each example is equipped with multi-level annotations, ranging from low-level camera-motion trajectories to high-level semantic instructions. The dataset also provides unified evaluation splits and task-specific metrics, supporting offline pretraining and fair evaluation of EWAs. Beyond offline supervision, a defining characteristic of an EWA is its interaction with the environment; training solely on offline data is therefore insufficient, especially for generalizing to scenes not covered in the training distribution. Building dedicated real interactive environments, however, is often prohibitively expensive. To address this, we propose a novel training scheme that employs a video world model as a low-cost environment proxy and performs interactive reinforcement-learning (RL) post-training of the EWA within it. Empirically, pretraining on EmbodiedWorld-200K substantially improves the open-world embodied planning ability of the EWA, and further RL post-training inside a world model yields clear gains on out-of-distribution scenes. The dataset, baseline checkpoints, and training and evaluation code are available at this https URL.
https://arxiv.org/abs/2610.25959
This paper proposes a command-aligned sampling distribution that incorporates navigation commands directly into the exploration process to improve the efficiency of sampling-based motion planning for quadcopters in three-dimensional environments. Inspired by the Language-Aided Subset Sampling Motion Planner, this paper extends command-aware subset sampling to aerial systems. Subset sampling is generalized to command-aligned regions, enabling structured 3D exploration while preserving probabilistic completeness. Natural language instructions are grounded into yaw-conditioned and altitude-aware geometric constraints using a prompt-based large language model for entity extraction and instruction validation. Extensive simulations in complex environments demonstrate that the proposed method generates collision-free, consistent trajectories while significantly reducing sampling effort compared to uniform RRT-based planners.
https://arxiv.org/abs/2610.34054
Construction robots must label building elements they can only partly see. We show that when occlusion at test time removes whole regions of a scene, rather than parts of an object as in training, point-cloud segmentation networks do not simply miss the hidden elements: they relabel them, and the errors collapse onto a single sink class. With fixed synthetic layouts the column absorbs up to 70% of all test points; with randomized layouts the sink moves to the stair, predicted at 4.5-5.4x its true share across three training seeds. Baseline mIoU falls to 0.15-0.27 (fixed) and 0.36-0.72 (randomized), and up to 269 whole objects vanish in a single test set. Appending 14 hand-computed geometric features per point (GPE) restores mIoU to 0.54-0.92 and removes 64-100% of whole-object losses in every run, for PointNet++ and a PTv3-style transformer in both layout regimes; on real S3DIS scans it removes every whole-wall loss (10 to 0). In an as-built column check computed from the predictions, GPE raises the share of correctly checked views from 17-58% to 71-92%. Feature permutation on fixed, randomized and real scenes explains the pattern: each class relies on whichever cue is stable in its training data, position for height-banded slabs and beams, intrinsic shape for walls and stairs once their position varies. Occlusion augmentation is a strong alternative on mIoU, but in every setting it loses more whole objects than GPE (e.g., 25-35 vs. 0).
https://arxiv.org/abs/2610.34040
Deep learning facilitates rapid single shot three dimensional (3D) reconstruction using fringe projection profilometry (FPP), but recovering accurate surface height from a single high frequency fringe image remains challenging because both long-range spatial consistency and fine geometric details must be preserved. Convolutional networks are limited in modeling long range dependencies, whereas window-based Transformers establish global interactions only progressively with increasing depth. To address these limitations, a hybrid Mamba Transformer network is proposed for fringe to height regression. The network adopts a Swin based U shaped architecture and introduces visual state space modeling at the intermediate resolution encoder stage. An axial and dilated vision state space (ADVSS) block is further developed to enhance prescan feature encoding through local, dilated, and axial depthwise convolutions while retaining four directional selective scanning. This design combines linear complexity long range modeling with direction aware preservation of local fringe structures. Experiments on a publicly available FPP dataset show that the proposed method outperforms hNet, SwinConvUNet, UHRNet, and HiDNet in mean absolute error(MAE), root mean square error (RMSE), absolute relative error, and structural similarity index measure (SSIM). Using only one deformed fringe image, the proposed method achieves an RMSE of 0.548 mm and an SSIM of 0.9985, reducing RMSE by 65.2% and 59.6% relative to UHRNet and HiDNet, respectively. These results demonstrate the effectiveness of combining selective state space modeling with hierarchical window based attention for accurate single-shot FPP reconstruction.
https://arxiv.org/abs/2610.33988
Language-aware 3D Gaussian Splatting (3DGS) has advanced language-driven 3D scene understanding by incorporating semantic and relational cues into reconstructed scenes. However, relation-aware grounding depends not only on representing such information, but also on whether the underlying scene-side evidence is reliable and sufficient. Multi-view semantic aggregation can incorporate weak observations, while object relations can remain under-observed along the available camera trajectory, leading to ambiguous evidence for target disambiguation. We present RelateGS, a structured language-aware Gaussian representation that selectively refines semantic and relational evidence for 3D visual grounding. RelateGS suppresses unreliable observations during semantic feature uplifting and consolidates multi-view object observations into a persistent 3D graph. The graph further identifies under-observed object relations and guides targeted re-querying of informative existing frames to complement their evidence. Experiments on Sr3D+ and Nr3D demonstrate competitive 3D grounding performance, improving the previous best by 7.9 and 1.7 percentage points at Acc@0.25, respectively.
https://arxiv.org/abs/2610.33868
Video world models (VWMs) are rapidly emerging as scalable neural simulators for robotic manipulation. However, most benchmarks only evaluate them as open-world video generators, using Vision-Language Models (VLMs) that lack strict 3D spatial and kinematic reasoning. To bridge this gap, we introduce RoboWorM, a comprehensive, deployment-aware benchmark that leverages known hardware priors such as robot kinematic trees and fixed camera configurations, to systematically examine structural and spatiotemporal fidelity. RoboWorM curates 1,605 episodes across single-arm, bimanual, and humanoid morphologies, spanning both Markovian and long-horizon non-Markovian tasks under single- and multi-view setups. To explicitly measure physical consistency, we propose two deterministic, VLM-free metrics: KIVA for intra-view kinematic stability, and RIGIS for multi-view geometric consistency. By exploiting intrinsic robotic invariants, KIVA improves hallucination detection alignment with human annotations by 25.8% relative to the strongest frontier VLMs, while RIGIS achieves a 130% higher Spearman correlation with human preferences. Furthermore, since real-world deployment requires low inference latency, we utilize RoboWorM to conduct the first large-scale audit of the quality-efficiency trade-off. Evaluating 9 state-of-the-art acceleration techniques across 3 leading world models (over 29,000 generated rollouts), we demonstrate how these acceleration methods can retain superficial visual quality while silently compromising deployment-critical physical constraints. Using our metrics, we achieve 2.3$\times$ maximum inference speed-up with minimal quality loss.
https://arxiv.org/abs/2610.33807
Feed-forward 3D foundation models have recently reshaped multi-view reconstruction, yet dynamic 4D understanding still often relies on large-scale motion supervision or hand-crafted, architecture-specific heuristics. We ask whether frozen 3D foundation model tokens already encode motion-relevant information that can be exposed by lightweight readout functions, rather than re-learning motion-specific features with high-capacity decoders. Through probing on three representative backbones, we find that static--dynamic separation is decodable from frozen token representations. Our rank-restricted and spectral analyses on $\pi^3$X reveal that the recovered motion cues are concentrated in a low-dimensional subspace. Building on this, we propose Probing-based Motion Distillation (PMD), which converts pairwise motion-state compatibility scores against a fixed anchor token into dense motion masks. Trained on only 160 YouTube-VOS videos using a single 16 GB GPU, PMD transfers zero-shot to DAVIS, SegTrackv2, and FBMS-59 without target-benchmark fine-tuning. With multi-view pretrained geometric backbones, PMD outperforms training-free heuristics and approaches substantially heavier supervised and self-supervised methods, suggesting that motion decoding from frozen 3D foundation models can be lightweight and data-efficient.
https://arxiv.org/abs/2610.33802
We present a principled, analytical framework for segmenting multiple independently moving rigid objects during single camera motion, built directly upon the OWL perception function. OWL encodes two fundamental visual motion cues, perceived looming $L$ and perceived rotation $\omega$, into a single closed-form representation of relative 3D structure. A key consequence of this structure is that the unit direction of relative translation $\hat{t}$ is analytically recoverable per image point from $L$ and $\omega$ alone. All points belonging to a non-rotating rigid body share the same $\hat{t}$, whereas points on different rigid bodies generally yield distinct values. This furnishes a natural segmentation criterion: clustering per-point $\hat{t}$ estimates partitions the visible scene into independently moving rigid bodies. Building on the 2D complex form of OWL, we derive the framework in 3D using quaternions, for a single moving camera. The approach is parallel, camera rotation-invariant, and requires no training data, no depth information, and no semantic priors.
https://arxiv.org/abs/2610.33789