AI Paper Atlas

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

AAAI 2026 · Video › Video generation · approach: World-model video generation · 12 citations (OpenAlex)

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 changedWhereMeasuredEffect
use ManipDreamer3D conditioning on SVD instead of This&ThatSVD-based video generator · Bridge V1+V2 testTrajError robot: 62.07 -> 17.40Improved
use ManipDreamer3D conditioning on SVD instead of DragAnythingSVD-based video generator · Bridge V1+V2 testFVD: 158.42 -> 143.33Improved
switch backbone from SVD to CogVideoX-5B (DiT)ManipDreamer3D · Bridge V1+V2 testFVD: 143.33 -> 93.98Improved
use ManipDreamer3D on CogVideoX-5B instead of RoboMasterCogVideoX-5B video generator · Bridge V1+V2 testTrajError obj: 24.16 -> 16.59Improved
use ManipDreamer3D(DiT) instead of RoboMaster on VBench temporal flickeringCogVideoX-5B video generator · VBenchTemporal Flickering: 98.27 -> 98.18No clear effect
use ManipDreamer3D(SVD) instead of This&That on aesthetic qualitySVD-based video generator · VBenchAesthetic Quality: 57.27 -> 52.46Hurt
use ManipDreamer3D(SVD) instead of This&That on imaging qualitySVD-based video generator · VBenchImaging Quality: 70.09 -> 69.24Hurt
use ManipDreamer3D(SVD) instead of This&That on subject consistencySVD-based video generator · VBenchSubject Consistency: 94.43 -> 95.39Improved
add trajectory optimization (collision, length, smoothness) to the A* initial path (ablation)ManipDreamer3D · qualitative (pumpkin out of sink)trajectory safetyImproved
add path-aware time reallocation with sine velocity profile (ablation)ManipDreamer3D · qualitative (velocity distribution of one example)velocity realismImproved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy