AI Paper Atlas

Research map / 3D vision / Face and shape

HairNet: Single-View Hair Reconstruction using Convolutional Neural Networks

Yi Zhou, Liwen Hu, Jun Xing, Weikai Chen, Han-Wei Kung, Xin Tong, Hao Li

ECCV 2018 · 3D vision › Face and shape · approach: Pixel-aligned implicit human and hand reconstruction · 86 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 visibility-adaptive weights to the loss (ablation)HairNet · Synthetic test set (100 hair models x 4 views)visible-part position error: 0.024 -> 0.017Improved
add visibility-adaptive weights to the loss (ablation)HairNet · Synthetic test set (100 hair models x 4 views)collision error: 3.5x10^-7 -> 2.26x10^-7Improved
add visibility-adaptive weights to the loss (ablation)HairNet · Synthetic test set (100 hair models x 4 views)invisible-part position error: 0.026 -> 0.027No clear effect
add collision loss (ablation)HairNet · Synthetic test set (100 hair models x 4 views)collision error: 3.26x10^-6 -> 2.26x10^-7Improved
add collision loss (ablation)HairNet · Synthetic test set (100 hair models x 4 views)visible-part position error: 0.019 -> 0.017Improved
add curvature loss (ablation)HairNet · Synthetic test set (100 hair models x 4 views)visible-part position error: 0.020 -> 0.017Improved
add curvature loss (ablation)HairNet · Synthetic test set (100 hair models x 4 views)invisible-part position error: 0.029 -> 0.027Improved
replace Chai et al. retrieval-and-refinement with HairNetChai et al. · Synthetic test set (100 hair models x 4 views)invisible-part position error: 0.040 -> 0.027Improved
replace Chai et al. retrieval-and-refinement with HairNetChai et al. · Time and space at 9K strandstotal time: 53 s -> 0.04 - 0.08 sImproved
replace Chai et al. database with HairNet networkChai et al. · Time and space at 9K strandstotal storage: 1 TiB -> 70 MiBImproved
replace nearest-neighbor retrieval by HairNetNN · Synthetic test set (100 hair models x 4 views)visible-part position error: 0.033 -> 0.017Improved
replace nearest-neighbor retrieval by HairNetNN · Synthetic test set (100 hair models x 4 views)collision error: 0 -> 2.26x10^-7Hurt

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