AI Paper Atlas

Research map / 3D vision / Face and shape

BCNet: Learning Body and Cloth Shape from A Single Image

Boyi Jiang, Juyong Zhang, Yang Hong, Jinhao Luo, Ligang Liu, Hujun Bao

ECCV 2020 · 3D vision › Face and shape · approach: Clothed human modeling · 181 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 displacement network (ablation)BCNet · Synthetic test setMED shirt (cm): 1.72 -> 0.91Improved
add displacement network (ablation)BCNet · Synthetic test setMED pant (cm): 1.59 -> 0.75Improved
add displacement network (ablation)BCNet · Synthetic test setMED skirt (cm): 2.46 -> 0.87Improved
add displacement network (ablation)BCNet · HD Texture test setMED shirt (cm): 1.97 -> 1.71Improved
add displacement network (ablation)BCNet · HD Texture test setMED pant (cm): 1.72 -> 1.42Improved
add displacement network (ablation)BCNet · HD Texture test setMED skirt (cm): 1.87 -> 1.65Improved
add interpenetration loss (ablation)BCNet · Qualitative test imagesinterpenetrationImproved
use single image instead of 8 views with post-optimization (vs MGN-8)BCNet · BUFF rough A-pose (21 scans)MED total (cm): 1.99 -> 1.35Improved
add post-optimization to Octopus-8 (8 views)BCNet · BUFF rough A-pose (21 scans)MED total (cm): 1.70 -> 1.31Improved
add post-optimization to MGN-8 (8 views)BCNet · BUFF rough A-pose (21 scans)MED total (cm): 1.99 -> 1.82Improved
compare BCNet with PIFu on Digital WardrobeBCNet · Digital Wardrobe (94 meshes)MED total (cm): 1.85 -> 1.80Mixed

Later papers that compared with this method

6 later accepted papers report BCNet as a baseline in their results tables; 5 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