AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling

YoungJoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs

ICLR 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 1 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
Combine the implicit body NeRF with image-based rendering and learned appearance blendingNIA · ZJU-MoCap, unseen subjects and posesPSNR: +1.0 dB PSNRImproved
Use NIA instead of NHP for cross-dataset generalizationZJU-MoCap-trained model evaluated on MonoCap · MonoCap, cross-dataset novel view synthesisPSNR: +1.6 dB PSNRImproved
Add the implicit body representation (ablation)NIA · ZJU-MoCap, unseen identities and posesPSNR: -1.63 dBImproved
Add image-based rendering (ablation)NIA · ZJU-MoCap, unseen identities and posesPSNR: -1.55 dBImproved
Use learned neural appearance blending instead of simple averaging (ablation)NIA · ZJU-MoCap, unseen identities and posesPSNR: +0.97 dBImproved
Use learned neural appearance blending instead of cosine-similarity weighted averaging (ablation)NIA · ZJU-MoCap, unseen identities and posesPSNR: +0.45 dBImproved
Increase the number of source views from 1 to 2 to 3 (ablation)NIA · ZJU-MoCap, novel view synthesisPSNRImproved

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