MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation

• URL: http://arxiv.org/abs/2602.09878v1
• Date: Tue, 10 Feb 2026 15:19:17 GMT
• Title: MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation
• Authors: Jiaxu Wang, Yicheng Jiang, Tianlun He, Jingkai Sun, Qiang Zhang, Junhao He, Jiahang Cao, Zesen Gan, Mingyuan Sun, Qiming Shao, Xiangyu Yue,
• Abstract summary: This work proposes a novel embodied 4D world model that enables geometrically consistent, arbitrary-view RGBD generation.<n>Experiments on three datasets demonstrate strong performance on both 4D scene generation and downstream manipulation.
• Score: 27.70398018267795
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely image-based forecasting or reasoning over partial 3D geometry, limiting their ability to predict complete 4D scene dynamics. This work proposes a novel embodied 4D world model that enables geometrically consistent, arbitrary-view RGBD generation: given only a single-view RGBD observation as input, the model imagines the remaining viewpoints, which can then be back-projected and fused to assemble a more complete 3D structure across time. To efficiently learn the multi-view, cross-modality generation, we explicitly design cross-view and cross-modality feature fusion that jointly encourage consistency between RGB and depth and enforce geometric alignment across views. Beyond prediction, converting generated futures into actions is often handled by inverse dynamics, which is ill-posed because multiple actions can explain the same transition. We address this with a test-time action optimization strategy that backpropagates through the generative model to infer a trajectory-level latent best matching the predicted future, and a residual inverse dynamics model that turns this trajectory prior into accurate executable actions. Experiments on three datasets demonstrate strong performance on both 4D scene generation and downstream manipulation, and ablations provide practical insights into the key design choices.

Related papers

• StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation [6.0744834626758495]
  StemVLA is a novel framework that explicitly incorporates both future-oriented 3D spatial knowledge and historical 4D representations into action prediction.<n>We show that StemVLA significantly improves long-horizon task success and state-of-the-art performance on the CALVIN ABC-D benchmark [46], achieving an average sequence length of XXX.
  arXiv  Detail & Related papers  (2026-02-27T06:43:37Z)
• Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis [53.48281548500864]
  Motion 3-to-4 is a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video.<n>Our model learns a compact motion latent representation and predicts per-frame trajectories to recover complete robustness, temporally coherent geometry.
  arXiv  Detail & Related papers  (2026-01-20T18:59:48Z)
• VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation [54.81449795163812]
  We develop a general VLA model with 4D awareness for temporally coherent robotic manipulation.<n>We extract visual features, embed 1D time into 3D positions for 4D embeddings, and fuse them into a unified visual representation via a cross-attention mechanism.<n>Within this framework, the designed visual action jointly make robotic manipulation spatially-smooth and temporally temporally coherent.
  arXiv  Detail & Related papers  (2025-11-21T12:26:30Z)
• DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation [52.136378691610524]
  We present DynaRend, a representation learning framework that learns 3D-aware and dynamics-informed triplane features.<n>By pretraining on multi-view RGB-D video data, DynaRend jointly captures spatial geometry, future dynamics, and task semantics in a unified triplane representation.<n>We evaluate DynaRend on two challenging benchmarks, RLBench and Colosseum, demonstrating substantial improvements in policy success rate, generalization to environmental perturbations, and real-world applicability across diverse manipulation tasks.
  arXiv  Detail & Related papers  (2025-10-28T10:17:11Z)
• Advances in 4D Representation: Geometry, Motion, and Interaction [21.99533577912307]
  We present a survey on 4D generation and reconstruction, a fast-evolving subfield of computer graphics.<n>We build our coverage of the domain from a unique and distinctive perspective of 4D representations.
  arXiv  Detail & Related papers  (2025-10-22T05:22:20Z)
• Geometry-aware 4D Video Generation for Robot Manipulation [28.709339959536106]
  We propose a 4D video generation model that enforces multi-view 3D consistency of videos by supervising the model with cross-view pointmap alignment during training.<n>This geometric supervision enables the model to learn a shared 3D representation of the scene, allowing it to predict future video sequences from novel viewpoints.<n>Compared to existing baselines, our method produces more visually stable and spatially aligned predictions across multiple simulated and real-world robotic datasets.
  arXiv  Detail & Related papers  (2025-07-01T18:01:41Z)
• TesserAct: Learning 4D Embodied World Models [66.8519958275311]
  We learn a 4D world model by training on RGB-DN (RGB, Depth, and Normal) videos.<n>This not only surpasses traditional 2D models by incorporating detailed shape, configuration, and temporal changes into their predictions, but also allows us to effectively learn accurate inverse dynamic models for an embodied agent.
  arXiv  Detail & Related papers  (2025-04-29T17:59:30Z)
• MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation [54.27399121779011]
  We present MVD-Fusion: a method for single-view 3D inference via generative modeling of multi-view-consistent RGB-D images. We show that our approach can yield more accurate synthesis compared to recent state-of-the-art, including distillation-based 3D inference and prior multi-view generation methods.
  arXiv  Detail & Related papers  (2024-04-04T17:59:57Z)
• DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention [50.11672196146829]
  3D object detection with surround-view images is an essential task for autonomous driving. We propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in multi-view images.
  arXiv  Detail & Related papers  (2022-12-15T14:18:47Z)
• Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training [3.8073142980733]
  We propose a novel framework for monocular 3D objects detection using only RGB images, called KM3D-Net. We design a fully convolutional model to predict object keypoints, dimension, and orientation, and then combine these estimations with perspective geometry constraints to compute position attribute.
  arXiv  Detail & Related papers  (2020-09-02T00:51:51Z)

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.