AI Paper Atlas

Research map / 3D vision / 3D generation

TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement

Keyang Zhou, Bharat Lal Bhatnagar, Jan Eric Lenssen, Gerard Pons-Moll

ECCV 2022 · 3D vision › 3D generation · approach: Hand-object interaction generation · 70 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 object-centric TOCH fields instead of hand-centric input (ablation)TOCH · GRAB-B (0.01 & 0.3)C-IoU (%): 18.9 -> 26.6Improved
use object-centric TOCH fields instead of hand-centric input (ablation)TOCH · GRAB-B (0.01 & 0.3)MPJPE (mm): 11.2 -> 10.3Improved
add dense hand-point correspondence to the TOCH field (ablation)TOCH · GRAB-B (0.01 & 0.3)C-IoU (%): 18.6 -> 26.6Improved
add dense hand-point correspondence to the TOCH field (ablation)TOCH · GRAB-B (0.01 & 0.3)MPJPE (mm): 12.2 -> 10.3Improved
add GRU temporal modeling instead of global feature aggregation (ablation)TOCH · GRAB-B (0.01 & 0.3)C-IoU (%): 20.4 -> 26.6Improved
add GRU temporal modeling (ablation)TOCH · GRAB-B (0.01 & 0.3)IV (cm^3): 1.87 -> 1.78Improved
test on objects seen in training (action-based split) instead of unseen objects (ablation)TOCH · GRAB-B (0.01 & 0.3)C-IoU (%): 26.6 -> 23.1Hurt
refine pose-dominant perturbation GRAB-R (0.3) with TOCHTOCH · GRAB-R (0.3)MPJPE (mm): 4.58 -> 9.58Hurt
refine translation-dominant perturbation with TOCHTOCH · GRAB-T (0.02)MPJPE (mm): 31.9 -> 12.3Improved
refine GRAB-R (0.3) with TOCH for contactTOCH · GRAB-R (0.3)C-IoU (%): 11.4 -> 26.6Improved
refine GRAB-T (0.02) with TOCH for penetrationTOCH · GRAB-T (0.02)IV (cm^3): 2.40 -> 2.50No clear effect
use TOCH instead of ContactOptTOCH · HO-3DIV (cm^3): 5.71 -> 4.66Improved

Later papers that compared with this method

2 later accepted papers report TOCH as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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