AI Paper Atlas

Research map / 3D vision / 3D generation

FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models

Jianglong Ye, Naiyan Wang, Xiaolong Wang

ICCV 2023 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 45 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 coordinate loss L_coord (ablation)FeatureNeRF (DINO) · ShapeNet Chair 2D part co-segmIoU: 75.39 -> 76.55Improved
add coordinate loss L_coord (ablation)FeatureNeRF (DINO) · ShapeNet Plane 2D part co-segmIoU: 72.83 -> 74.60Improved
use internal NeRF features instead of final output feature (ablation)FeatureNeRF (DINO) · ShapeNet Chair 2D part co-segmIoU: 74.62 -> 76.55Improved
use internal NeRF features instead of final output feature (ablation)FeatureNeRF (DINO) · ShapeNet Plane 2D part co-segmIoU: 72.29 -> 74.60Improved
distill DINO features into NeRF featureNeRF Feature · ShapeNet Chair 2D part co-segmIoU: 72.02 -> 76.55Improved
distill DINO features into NeRF featureNeRF Feature · ShapeNet Chair 3D part co-segmIoU: 65.23 -> 73.85Improved
distill diffusion features instead of DINO featuresFeatureNeRF · ShapeNet Chair 2D part co-segmIoU: 76.55 -> 65.39Hurt
distill diffusion features into NeRF featureNeRF Feature · ShapeNet Bottle 2D part co-segmIoU: 55.87 -> 53.91Hurt
distill DINO features (novel-view)NeRF Feature · ShapeNet Bottle novel-view 2D part segmIoU: 87.14 -> 87.89No clear effect
distill diffusion features (novel-view)NeRF Feature · ShapeNet Plane novel-view 2D part segmIoU: 69.45 -> 59.16Hurt
add feature distillation to PixelNeRFPixelNeRF · ShapeNet Chair novel-view synthesisPSNR: 23.29 -> 23.20No clear effect
FeatureNeRF (DINO) vs DINO baselineDINO Baseline · ShapeNet Chair 3D part co-segmIoU: 52.67 -> 73.85Improved

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