AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Learning Compositional Radiance Fields of Dynamic Human Heads

Ziyan Wang, Timur Bagautdinov, Stephen Lombardi, Tomas Simon, Jason Saragih, Jessica Hodgins, Michael Zollhofer

CVPR 2021 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 74 citations (OpenAlex)

Check 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 the compositional local-animation-code radiance field rather than Neural VolumesDynamic human head rendering · Sequence1–Sequence4MSE: 46.19 -> 34.01; 52.11 -> 42.65; 83.07 -> 79.29; 40.47 -> 27.62Improved
Use the compositional local-animation-code radiance field rather than global-code NeRFDynamic human head rendering · Sequence1–Sequence4MSE: 43.34 -> 34.01; 46.89 -> 42.65; 90.45 -> 79.29; 35.52 -> 27.62Improved
Condition the radiance field on spatially varying local animation codes instead of only a global animation code (ablation)Ours and temporally conditioned NeRF · training sequences of 1, 40, 120, 240, and 360 framesMSEImproved
Increase the coarse voxel feature resolution (ablation)Ours · Sequence-length reconstruction evaluationMSEImproved
Reduce the coarse voxel feature resolution (ablation)Ours · Sequence-length reconstruction evaluationMSEHurt
Replace hierarchical sampling with simple sampling (ablation)Ours · single sentenceRuntime: 14.30s -> 3.6sImproved
Replace hierarchical sampling with simple sampling (ablation)Ours · single sentenceSSIM: 0.9090 -> 0.9113No clear effect
Replace hierarchical sampling with simple sampling (ablation)NeRF · single sentenceRuntime: >25s -> 19.69sImproved
Replace hierarchical sampling with simple sampling (ablation)NeRF · single sentenceSSIM: 0.8898 -> 0.8886No clear effect
Use image input rather than sparse 2D keypoints, without encoder fine-tuning (ablation)Novel content synthesis encoder · novel contentMSE: 58.52 -> 55.86Improved
Fine-tune the encoder (ablation)Keypoints-driven novel content synthesis · novel contentMSE: 58.52 -> 35.12Improved
Fine-tune the image encoder (ablation)Image-driven novel content synthesis · novel contentMSE: 55.86 -> 34.86Improved

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