AI Paper Atlas

Research map / 3D vision / Human pose estimation

Novel-View Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views

Wentian Qu, Zhaopeng Cui, Yinda Zhang, Chenyu Meng, Cuixia Ma, Xiaoming Deng, Hongan Wang

ICCV 2023 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 27 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 online joint model fitting with render and pose losses (ablation)hand-object rendering · HandObject renderingPSNR: 22.07 -> 22.17Improved
add interaction loss (SDF penetration and contact) (ablation)online fitting · HandObject renderingPSNR: 22.17 -> 22.25Improved
add interaction loss (ablation)online fitting · Synthetic DexYCB master-chef-canpenetration depth (mm): 9.65 -> 6.09Improved
add interaction loss (ablation)online fitting · HandObject (bean-can, box, cup, meat-can)hand MPJPE: bean-can 7.72 -> 8.07Mixed
add smooth loss (ablation)video fitting · HandObjectAcc-V: 10.07 -> 6.35Improved
add stable contact loss (ablation)video fitting with smooth loss · HandObjectPCI (%): 36.37 -> 51.18Improved
add stable contact loss (ablation)video fitting with smooth loss · Synthetic DexYCBAcc-J: 6.78 -> 7.51Hurt
use SDF-based pre-built hand model instead of A-NeRF density hand model (ablation)hand-object fitting · HandObject (8 views)object AD: 20.94 -> 15.95Improved
fit with color loss on neural models instead of untextured mesh fitting (ablation)pose refinement · HandObject (8 views)hand MPJPE: 20.60 -> 10.80Improved
refine LT hand pose with online model fittingLT · HandObject (8 views)hand MPJPE: 9.66 -> 9.09Improved
pre-built hand and object models as priors for sparse-view renderingnovel view synthesis · HandObject (3 views)PSNR: 18.70 -> 22.20 vs InfoNeRFImproved

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