RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction

• URL: http://arxiv.org/abs/2608.28718v1
• Date: Fri, 28 Aug 2026 09:44:13 GMT
• Title: RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction
• Abstract summary: We introduce RoboPhys-3D, a 3D-grounded embodied world model (EWM) benchmark built on RoboTwin 2.0.<n>A defining feature of RoboPhys-3D is that generated and ground-truth videos are processed through the same 3D reconstruction pipeline.<n>The benchmark organizes 50 complementary metrics into 18 sub-dimensions across four levels: pixel-level fidelity, 3D geometry consistency, state-level understanding, and task-level completeness.
• Score: 24.674633972725804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video world models increasingly serve as data engines, action planners, and simulators for embodied AI, but conventional embodied world model (EWM) benchmarks lack a unified 3D-grounded protocol for establishing whether generated rollouts preserve the underlying 3D scene state or translate into executable actions. We introduce RoboPhys-3D, a 3D-grounded EWM benchmark built on RoboTwin 2.0, covering 50 manipulation tasks across four regimes, with 5,000 episodes and 25,000 multi-view ground-truth videos. A defining feature of RoboPhys-3D is that generated and ground-truth videos are processed through the same 3D reconstruction pipeline, enabling reconstruction-induced error to be distinguished from generation-induced error. The RoboPhys-3D benchmark organizes 50 complementary metrics into 18 sub-dimensions across four levels: pixel-level fidelity, 3D geometry consistency, state-level understanding, and task-level completeness. We further introduce Average Full Score, a hierarchical score averaging all 50 metrics for comprehensive evaluation, and RoboPhyscore, a compact task-aligned score averaging the metrics most strongly correlated with task success. Among the four representative video world models, Cosmos 3 achieves the highest RoboPhyscore (0.6330, 92.7% of ground truth), while state- and execution-grounded metrics reveal substantial failures that perceptual and vision-language model-based judgments fail to capture. RoboPhyscore further exhibits strong agreement with human evaluation (Pearson r = 0.9761 and Spearman \r{ho} = 0.8962), demonstrating the importance of grounded, execution-aware evaluation for EWM capability.

Related papers

• RigidBench: Evaluating Rigid-Body Physics in Video Generation Models [16.53417077740312]
  We introduce a simulator-grounded benchmark that compares a generated continuation with a reference rollout from the same initial frame and motion description.<n>We evaluate eight models on the same 100 examples with ten measurements that keep these aspects separate.<n>Full fine-tuning reduces 3D trajectory error by about 20% with almost no change in SSIM.
  arXiv  Detail & Related papers  (2026-08-16T06:05:20Z)
• KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding [58.541098216700796]
  evaluating the physical consistency of embodied world models is a critical open challenge.<n>Existing frameworks almost exclusively rely on Inverse Dynamics Models(IDMs) for action extraction.<n>We present KineBench, an IDM-free closed-loop benchmark for EWMs.
  arXiv  Detail & Related papers  (2026-07-22T08:04:17Z)
• Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation [76.16065370700488]
  We introduce Lift3D-VLA, a unified VLA framework that equips models with explicit 3D point cloud reasoning and enables temporally coherent action generation.<n>We show that Lift3D-VLA achieves 10.8% and 11.1% higher mean success rates on MetaWorld and RLBench than the best-performing prior VLA methods.
  arXiv  Detail & Related papers  (2026-07-07T17:59:47Z)
• WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models [37.59051701511746]
  We introduce WorldRoamBench, an open-world benchmark for long-horizon stability across four dimensions.<n>The benchmark comprises 600+ test cases across Nature, Urban, and Indoor scenes in first/third-person views with WASD 10-60s continuous interaction.
  arXiv  Detail & Related papers  (2026-06-30T13:51:44Z)
• GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors [113.71148915419246]
  We present GRAIL, a digital generation pipeline that composes 3D assets, simulator-ready scenes, and priors from video foundation models (VFMs) to synthesize interactions without rebuilding physical environments or teleoperating the robot.<n>GRAIL starts from fully specified 3D configurations in which object geometry, camera parameters, metric scale, environment depth, and a robot-proportioned character are known before video generation and reused during reconstruction.<n>We retarget the recovered motions to a humanoid robot and train complementary task-general morphology trackers.<n>GRAIL produces over 20,000 sequences spanning pick-up, object manipulation, sitting
  arXiv  Detail & Related papers  (2026-06-03T17:57:45Z)
• GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation [72.52773248997929]
  Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time.<n>We present GEM-4D, a geometry-grounded video world model that injects dense 4D correspondence supervision into the video generative backbone during training.<n>In inverse dynamics module converts correspondence-consistent video rollouts into executable robot trajectories, enabling direct deployment in both real-world and simulated manipulation.
  arXiv  Detail & Related papers  (2026-05-20T21:36:44Z)
• PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learning [5.308328605042682]
  360 panoramic images are increasingly used in virtual reality, autonomous driving, and robotics for holistic scene understanding.<n>Current Vision-Language Models (VLMs) struggle with 3D spatial reasoning on Equirectangular Projection (ERP) images due to geometric distortion and limited 3D supervision.<n>We introduce PanoEnv, a large-scale VQA benchmark built from synthetic 3D environments.<n>Our 7B model achieves new state-of-the-art performance, improving overall accuracy to 52.93% (+3.59%) and open-ended accuracy to 14.83% while maintaining structured-task performance.
  arXiv  Detail & Related papers  (2026-02-25T15:12:17Z)
• E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models [78.1674905950243]
  We present the first comprehensive benchmark for 3D geometric foundation models (GFMs)<n>GFMs directly predict dense 3D representations in a single feed-forward pass, eliminating the need for slow or unavailable precomputed camera parameters.<n>We evaluate 16 state-of-the-art GFMs, revealing their strengths and limitations across tasks and domains.<n>All code, evaluation scripts, and processed data will be publicly released to accelerate research in 3D spatial intelligence.
  arXiv  Detail & Related papers  (2025-06-02T17:53:09Z)
• DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos [76.01906393673897]
  We propose a self-supervised method to jointly learn 3D motion and depth from monocular videos. Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion. Our model delivers superior performance in all evaluated settings.
  arXiv  Detail & Related papers  (2024-03-09T12:22:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.