AI Paper Atlas

Research map / 3D vision / Face and shape

DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction

Dae-Young Song, HeeKyung Lee, Jeongil Seo, Donghyeon Cho

CVPR 2023 · 3D vision › Face and shape · approach: Clothed human modeling · 26 citations (OpenAlex)

Read the paper

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 the SMPL volume with projected front/back depth maps as the 3D priorDIFu versus PaMIR · THuman2.0P2S: 4.071 -> 2.992Improved
replace the SMPL volume with projected front/back depth maps as the 3D priorDIFu versus ICON · BUFFP2S: 3.621 -> 3.375Improved
use the Ladv-trained hallucinator at inference while training with the non-adversarial hallucinator (ablation)DIFu · THuman2.0P2S: 3.331 -> 2.992Improved
use the Ladv-trained hallucinator at inference while training with the non-adversarial hallucinator (ablation)DIFu · BUFFP2S: 3.465 -> 3.374Improved
use the Ladv-trained hallucinator during occupancy-network training (ablation)DIFu · THuman2.0P2S: 2.992 -> 3.484Hurt
use the Ladv-trained hallucinator during occupancy-network training (ablation)DIFu · BUFFP2S: 3.374 -> 3.525Hurt
add the SMPL voxel encoder fS to the depth estimator (ablation)DIFu · THuman2.0P2S: 3.214 -> 2.992Improved
add the SMPL voxel encoder fS to the depth estimator (ablation)DIFu · THuman2.0Chamfer: 3.146 -> 2.952Improved
add the SMPL voxel encoder fS to the depth estimator (ablation)DIFu · THuman2.0Normal: 0.124 -> 0.119Improved
add the SMPL voxel encoder fS to the depth estimator (ablation)DIFu · THuman2.0MSE: 0.084 -> 0.082Improved
add the SMPL voxel encoder fS to the depth estimator (ablation)DIFu · THuman2.0LPIPS: 0.126 -> 0.124Improved

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