AI Paper Atlas

Research map / 3D vision / Face and shape

PointAvatar: Deformable Point-Based Head Avatars From Videos

Yufeng Zheng, Wang Yifan, Gordon Wetzstein, Michael J. Black, Otmar Hilliges

CVPR 2023 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 167 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
Use deformable point-based avatars instead of implicit avatar representationsPointAvatar · Lab-capture sequencesLPIPS: 0.178; 0.126 -> 0.094Improved
Use deformable point-based avatars instead of implicit avatar representationsPointAvatar · Casual videosLPIPS: 0.261; 0.187 -> 0.145Improved
Use deformable point-based avatars instead of implicit avatar representationsPointAvatar · Lab-capture sequencesPSNR: 22.4; 22.7 -> 26.6Improved
Use deformable point-based avatars instead of implicit avatar representationsPointAvatar · Casual videosPSNR: 18.7; 19.6 -> 22.3Improved
Add albedo-shading disentanglement (ablation)PointAvatar · Facial geometrygeometry detailImproved
Estimate canonical point normals from an SDF rather than neighboring-point planes (ablation)PointAvatar · Detailed regions including hair, eyes, and mouthnormal smoothnessImproved
Transform normals with the deformation Jacobian rather than only the rotation matrix (ablation)PointAvatar · Deformed facial geometry, including the nasal line when smilingnormal accuracyImproved
Add VGG feature loss to per-pixel L1 loss (ablation)PointAvatar · Avatar renderingphoto-realismImproved
Add a freely learned canonical offset instead of forcing points into predefined FLAME canonical space (ablation)PointAvatar · Canonical geometry and novel head posesgeneralizationImproved
Use two-stage deformation rather than a single-stage mapping (ablation)PointAvatar · Avatar geometry optimizationgeometry accuracyImproved
Use a point-based representation rather than a mesh-based representationPointAvatar · Eyeglasses and thin hair structuresgeometry detailImproved

Later papers that compared with this method

15 later accepted papers report PointAvatar as a baseline in their results tables; 15 of them report a better number on most of the results they share with it.

7 more not listed.

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