Research map / Video / Video generation
ManipDreamer3D: Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory
Ying Li, Xiaobao Wei, Xiaowei Chi, Yuming Li, Zhongyu Zhao, Hao Wang, Ningning Ma, Ming Lu, Sirui Han
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ManipDreamer3D conditioning on SVD instead of This&That | SVD-based video generator · Bridge V1+V2 test | TrajError robot: 62.07 -> 17.40 | Improved |
| use ManipDreamer3D conditioning on SVD instead of DragAnything | SVD-based video generator · Bridge V1+V2 test | FVD: 158.42 -> 143.33 | Improved |
| switch backbone from SVD to CogVideoX-5B (DiT) | ManipDreamer3D · Bridge V1+V2 test | FVD: 143.33 -> 93.98 | Improved |
| use ManipDreamer3D on CogVideoX-5B instead of RoboMaster | CogVideoX-5B video generator · Bridge V1+V2 test | TrajError obj: 24.16 -> 16.59 | Improved |
| use ManipDreamer3D(DiT) instead of RoboMaster on VBench temporal flickering | CogVideoX-5B video generator · VBench | Temporal Flickering: 98.27 -> 98.18 | No clear effect |
| use ManipDreamer3D(SVD) instead of This&That on aesthetic quality | SVD-based video generator · VBench | Aesthetic Quality: 57.27 -> 52.46 | Hurt |
| use ManipDreamer3D(SVD) instead of This&That on imaging quality | SVD-based video generator · VBench | Imaging Quality: 70.09 -> 69.24 | Hurt |
| use ManipDreamer3D(SVD) instead of This&That on subject consistency | SVD-based video generator · VBench | Subject Consistency: 94.43 -> 95.39 | Improved |
| add trajectory optimization (collision, length, smoothness) to the A* initial path (ablation) | ManipDreamer3D · qualitative (pumpkin out of sink) | trajectory safety | Improved |
| add path-aware time reallocation with sine velocity profile (ablation) | ManipDreamer3D · qualitative (velocity distribution of one example) | velocity realism | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DragAnything — Drag Anything: Motion Control for Anything using Entity Representation (ECCV 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation (ICLR 2025 · similarity 0.88)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.88)
- Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets (ICLR 2025 · similarity 0.87)
- PDFactor: Learning Tri-Perspective View Policy Diffusion Field for Multi-Task Robotic Manipulation (CVPR 2025 · similarity 0.87)
- DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation (NeurIPS 2025 · similarity 0.87)
- ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
