AI Paper Atlas

Research map / 3D vision / 3D generation

FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision

Tobias Kirschstein, Simon Giebenhain, Matthias Nießner

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 7 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 bias sinks when mixing monocular and multi-view data (ablation)FlexAvatar · Ava256 (single-image, ablation)PSNR: 14.5 -> 17.2Improved
add bias sinks when mixing monocular and multi-view data (ablation)FlexAvatar · Ava256 (single-image, ablation)LPIPS: 0.351 -> 0.285Improved
add multi-view 3D data to monocular-only training (ablation)FlexAvatar · Ava256 (single-image, ablation)PSNR: 13.7 -> 17.2Improved
add monocular 2D data to multi-view-only training (ablation)FlexAvatar · Ava256 (single-image, ablation)CSIM: 0.119 -> 0.621Improved
add StyleGAN-PixelShuffle upsampler (ablation)FlexAvatar · Ava256 (single-image, ablation)PSNR: 17.1 -> 17.2Improved
add StyleGAN-PixelShuffle upsampler (ablation)FlexAvatar · Ava256 (single-image, ablation)AKD: 7.03 -> 6.34Improved
add per-person fitting of avatar code (ablation)FlexAvatar · Ava256 (single-image, ablation)CSIM: 0.621 -> 0.682Improved
add per-person fitting of avatar code (ablation)FlexAvatar · Ava256 (single-image, ablation)PSNR: 17.2 -> 16.9Hurt
use FlexAvatar instead of LAMLAM · VFHQ-Test (self-reenactment)AKD: 2.059 -> 2.965Hurt
use FlexAvatar instead of LAM (single-image)LAM · Ava256 (single-image)PSNR: 13.1 -> 16.9Improved
use FlexAvatar instead of Avat3r (few-shot)Avat3r · Ava256 (few-shot, 4 images)LPIPS: 0.310 -> 0.218Improved
use FlexAvatar instead of RGBAvatarRGBAvatar · NeRSemble monocular benchmarkLPIPS: 0.181 -> 0.156Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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