AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

DexMV: Imitation Learning for Dexterous Manipulation from Human Videos

Yuzhe Qin, Yueh-Hua Wu, Shaowei Liu, Hanwen Jiang, Ruihan Yang, Yang Fu, Xiaolong Wang

ECCV 2022 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 152 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
add demonstrations (DAPG) to RLTRPO · Relocate mustard bottlesuccess rate: 0.06 -> 0.93Improved
add demonstrations (SOIL) to RLTRPO · Relocate sugar boxsuccess rate: 0.00 -> 0.67Improved
use DAPG instead of SOILimitation learning · Relocate sugar boxsuccess rate: 0.67 -> 0.00Hurt
use DAPG state-action demos instead of SOIL state-onlyimitation learning · Poursuccess (%): 3.5 -> 27.2Improved
use DAPG instead of SOILimitation learning · Place Insideinside score: 27.9 -> 31.3Improved
increase demonstrations from 10 to 100 (ablation)SOIL · Relocate tomato soup cansuccess rate: 0.36 -> 1.00Improved
increase demonstrations from 50 to 100 (ablation)SOIL · Relocate tomato soup cansuccess rate: 0.59 -> 1.00Improved
use proposed retargeting instead of fingertip mapping (ablation)SOIL · Relocate tomato soup cansuccess rateImproved
add L2 smoothness norms to retargeting objective (ablation)SOIL · Relocate tomato soup cansuccess rateImproved
use two cameras with post-processing for hand pose (ablation)SOIL · Relocate tomato soup cansuccess (%): 66.7 -> 93.3Improved
use dual camera instead of single camera (ablation)SOIL · Relocate tomato soup cansuccess (%): 66.7 -> 84.7Improved
scale object size and friction in sim (ablation)SOIL · Relocate tomato soup cansuccess rateNo clear effect

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