AI Paper Atlas

Research map / 3D vision / Face and shape

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

Dongwei Pan, Long Zhuo, Jingtan Piao, Huiwen Luo, Wei Cheng, Yuxin WANG, Siming Fan, Shengqi Liu, Lei Yang, Bo Dai, Ziwei Liu, Chen Change Loy and 4 more

NeurIPS 2023 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 5 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
Train with random source views rather than fixed source viewsGeneralizable NVS methods · Unseen expressions and unseen identitiesPSNRImproved
Increase human-head appearance and geometry complexitySingle-ID NVS methods · Normal, deformable-accessory, and complex-accessory casesPSNR: 24.71 -> 20.54Hurt
Use a surface representation instead of volumetric representationSingle-ID NVS · OverallPSNR: 23.21 -> 24.67Improved
Use PointAvatar's point-based representation with an implicit representationNovel expression synthesis · Normal and hard expressionsPSNR: 22.61 -> 24.57; 21.91 -> 25.05Improved
Use point-based representation for subtle facial motionsPointAvatar · Novel expression synthesisPSNRHurt
Increase hair geometry complexity from short or long hair to curlsHair-rendering methods · Static and dynamic novel-view hair renderingPSNRHurt
Use NSFF instead of NR-NeRF for time interpolation of dynamic hairHair rendering · Time-InterpolationLPIPS: 0.124 -> 0.098Improved
Use Instant-NGP instead of NeuS for static hair renderingHair rendering · Static Rendering, OverallPSNR: 21.76 -> 23.75Improved
Use MVP instead of NV for dynamic hair renderingHair rendering · Dynamic Rendering, OverallPSNR: 20.32 -> 22.61Improved
Replace e4e inversion with Restyle_e4e inversionHairCLIP hair editing · Normal hairstylesID-score: 0.57 -> 0.58Improved
Use PTI inversion rather than e4e inversionText-based hair editing · Normal hairstylesID-score: 0.57 -> 0.88Improved
Evaluate on deformable-accessory images instead of normal hairstylesHair editing inversion methods · Hard casesID-score: 0.88 -> 0.86Hurt

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