AI Paper Atlas

Research map / 3D vision / Face and shape

Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image

Xingyu Liu, Pengfei Ren, Jingyu Wang, Qi Qi, Haifeng Sun, Zirui Zhuang, Jianxin Liao

ECCV 2024 · 3D vision › Face and shape · approach: Pixel-aligned implicit human and hand reconstruction · 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
replace pixel-aligned features with 3D point-aligned features (3D PIFu) (ablation)RGB-D SDF reconstruction · DexYCBHand Chamfer distance CDh (cm2): 0.299 -> 0.280Improved
add point cloud feature refinement via coarse-level SDF (ablation)3D PIFu model · DexYCBObject Chamfer distance CDo (cm2): 1.56 -> 1.26Improved
add surface-aware efficient reconstruction (sparse SDF queries) (ablation)full model · DexYCBReconstruction time (s): 3.44 -> 1.26 s; 2.1M -> 89.8K sampling pointsImproved
add SER to full model (ablation)full model · DexYCBHand Chamfer distance CDh (cm2): 0.272 -> 0.267 (Table 1 ID 3 vs 4); identical 0.267 with and without sparse samplingNo clear effect
use heatmap only for sparse queries instead of heatmap plus point cloud (ablation)SER · DexYCBHand Chamfer distance CDh (cm2): 0.267 -> 0.279Hurt
add RGB-D input instead of RGB only with pixel-aligned features (ablation)SDF baseline · DexYCBObject Chamfer distance CDo (cm2): 2.04 -> 1.50Improved
use proposed method instead of adding SA-Gate RGB-D fusion to gSDFRGB-D hand-object reconstruction · DexYCBObject Chamfer distance CDo (cm2): 1.28 -> 1.24Improved
use coarse-to-fine RGB-D SDF instead of gSDFObMan · ObManObject Chamfer distance CDo (cm2): 3.14 -> 0.51Improved

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