AI Paper Atlas

Research map / 3D vision / Face and shape

Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360°

Yuxiao He, Yiyu Zhuang, Yanwen Wang, Yao Yao, Siyu Zhu, Xiaoyu Li, Qi Zhang, Xun Cao, Hao Zhu

ECCV 2024 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars

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
optimize neural texture instead of texture code, with shape fixed from landmarks, for single-image fittingHead360 fitting · single-image fitting on SynHead100PSNR / SSIM / LPIPS / CSIM: PSNR 17.41 vs 17.18 (PanoHead re-trained)Improved
use hex-planes instead of tri-planes (ablation)Head360 representation · generated resultsLPIPS (x0.01): 9.54 -> 7.31 (no-refine row)Improved
use mesh + neural texture + hex-planes instead of conditioned vanilla NeRF (ablation)Head360 representation · generated resultsPSNR (dB): 24.44 -> 28.92Improved
add RefineNet (ablation)Head360 · generated resultsPSNR (dB) and LPIPS: PSNR 28.92 -> 28.27; LPIPS 7.31 -> 6.31Mixed
add hair detachment two-branch training (ablation)Head360 · hair swappingPSNR (dB): 20.04 -> 21.86Improved
add hair detachment two-branch training (ablation)Head360 · hair swappingLPIPS (x0.01): 15.89 -> 10.51Improved
optimize shape code and texture code simultaneously or iteratively with GAN inversion (ablation)Head360 fitting · single-image fittingfitting qualityHurt

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