AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

CodeNeRF: Disentangled Neural Radiance Fields for Object Categories

Wonbong Jang, Lourdes Agapito

ICCV 2021 · 3D vision › NeRF and radiance fields · approach: NeRF for scene decomposition and understanding · 176 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
use ground-truth camera pose at test time instead of jointly optimizing poseCodeNeRF · ShapeNet-SRN Chairs 1-viewPSNR: 22.39 -> 23.66Improved
use ground-truth camera pose at test time instead of jointly optimizing poseCodeNeRF · ShapeNet-SRN Cars 1-viewPSNR: 22.73 -> 23.80Improved
exclude pose-estimation outliers from evaluationCodeNeRF · ShapeNet-SRN Chairs 1-viewPSNR: 22.39 -> 23.11Improved
exclude pose-estimation outliers from evaluationCodeNeRF · ShapeNet-SRN Cars 1-viewPSNR: 22.73 -> 23.17Improved
add a second input viewCodeNeRF (GT pose) · ShapeNet-SRN ChairsPSNR: 23.66 -> 25.63Improved
add a second input viewCodeNeRF (GT pose) · ShapeNet-SRN CarsPSNR: 23.80 -> 25.71Improved
CodeNeRF with GT pose versus PixelNeRFCodeNeRF (GT pose) · ShapeNet-SRN Cars 1-viewPSNR: 23.17 -> 23.80Improved
CodeNeRF with GT pose versus PixelNeRFCodeNeRF (GT pose) · ShapeNet-SRN Chairs 1-viewPSNR: 23.72 -> 23.66Hurt
feed viewing direction to first layer with the shape code (M1) instead of the late texture branch (ablation)CodeNeRF · texture editing with fixed shape codetexture fidelityHurt
feed shape and texture codes jointly into the first network (single embedding, M2) instead of separate branches (ablation)CodeNeRF · texture editing with fixed shape codeshape consistencyHurt

Later papers that compared with this method

5 later accepted papers report CodeNeRF as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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