AI Paper Atlas

Research map / 3D vision / Face and shape

Detailed Avatar Recovery From Single Image

Hao Zhu, Xinxin Zuo, Haotian Yang, Sen Wang, Xun Cao, Ruigang Yang

TPAMI 2021 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 23 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
crop windows around handles instead of full image as joint net input (ablation)HMD joint stage · WILDsil IoU: 68.3% -> 70.7%Improved
crop windows around handles instead of full image as joint net input (ablation)HMD joint stage · WILD2D joint error pixel: 9.85 -> 8.81Improved
crop windows instead of full image as anchor net input (ablation)HMD anchor stage · WILDsil IoU: 70.1% -> 71.3%Improved
combine joint and anchor deformation instead of anchor only (ablation)HMD · WILDsil IoU: 71.3% -> 76.5%Improved
add joint-level and anchor-level deformation to HMR initial shape (ablation)HMD · WILDsil IoU: 67.6% -> 76.5%Improved
add photometric loss to ShadingNet (ablation)ShadingNet · captured depth datasetsurface error mm: 1.346 -> 1.129Improved
add ground-truth silhouette as inputHMD anchor · WILDsil IoU: 76.5 -> 82.4Improved
add random perturbation augmentation to texture training data (ablation)texture synthesis · SURREALPSNR: 17.62 -> 19.65Improved
add flow network before refinement (ablation)texture synthesis · SURREALPSNR: 19.48 -> 19.65Improved
add symmetry-flipped texture input to refinement (ablation)texture synthesis · SURREALPSNR: 19.58 -> 19.65Improved
add vertex-level deformation with shading net after anchor stage (ablation)HMD · SYN3D err full mm: 47.18 -> 44.75Improved
add vertex-level deformation after anchor stage (ablation)HMD · RECON3D err visible mm: 39.73 -> 41.76Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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