AI Paper Atlas

Research map / 3D vision / 3D generation

PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation

Peng Yun, Shouwang Huang, Hao Li, Jinxi Li, Jianan Wang, Bo Yang

ECCV 2026 · 3D vision › 3D generation · approach: Learning physics from video · 1 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
incorporate predicted 3D future dynamics into the 3DFA policy3DFA · PhysMani-Bench (16 tasks)mean success rate (%): 37.8 -> 45.9Improved
remove velocity components D_t from future-aware tokens (ablation)PhysMani · PhysMani-Bench ablation protocolmean success rate (%): 45.4 -> 37.9Hurt
add learnable query token L instead of self-attention for dynamics fusion (ablation)PhysMani · PhysMani-Bench ablation protocolmean success rate (%): 40.8 -> 45.4Improved
concatenate 2D optical flow to RGB input of 3DFA3DFA · PhysMani-Bench (16 tasks)mean success rate (%): 37.8 -> 37.5No clear effect
reduce world-model optimization iterations T from 50 to 40/30/20/10 (ablation)PhysMani · PhysMani-Bench (16 tasks)mean success rate (%)No clear effect
use PhysMani online world model instead of FreeGave for future prediction (1st frame)FreeGave · Future frame predictionPSNR: 19.47 -> 26.90Improved
use PhysMani online world model instead of FreeGave for 10th future frameFreeGave · Future frame predictionPSNR: 17.89 -> 20.00Improved
add PhysMani future dynamics to 3DFA on real robot3DFA · Real-world dynamic tasks (4 tasks)mean success rate (%): 45.3 -> 62.5Improved
add PhysMani future dynamics to 3DFA on Beat Buzz3DFA · PhysMani-Bench normal speed, task Beat Buzzsuccess rate (%): 82.5 -> 78.3No clear effect
use VLA pi0.5 instead of 3D policies on high-speed variantspi0.5 · PhysMani-Bench (16 tasks)mean success rate (%): 37.8 -> 8.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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