AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Decomposing NeRF for Editing via Feature Field Distillation

Sosuke Kobayashi, Eiichi Matsumoto, Vincent Sitzmann

NeurIPS 2022 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 102 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 distilled feature field branchNeRF · Replica novel view synthesisPSNR: 32.87 -> 32.85No clear effect
distill LSeg features into 3D feature field vs supervised MinkowskiNet423D semantic segmentation · ReplicamIoUImproved
increase feature loss weight lambda x10 (ablation)DFF · Replica novel view synthesisPSNR: 32.85 -> 32.68Hurt
increase feature loss weight lambda x10 (ablation)DFF coarse branch · Replica segmentationmIoU: 0.562 -> 0.565No clear effect
train feature field with coarse instead of fine sampling (ablation)DFF · Replica segmentationmIoU: 0.553 -> 0.562Improved
independent lightweight feature MLP instead of branch (ablation)DFF · Replica segmentationmIoU: 0.562 -> 0.544No clear effect

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