AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

DiffusioNeRF: Regularizing Neural Radiance Fields With Denoising Diffusion Models

Jamie Wynn, Daniyar Turmukhambetov

CVPR 2023 · 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 an RGBD diffusion prior to the geometric baseline (ablation)Instant NGP NeRF · DTU all viewsMean Chamfer-L1: 1.36 -> 1.21Improved
Add an RGBD diffusion prior to the geometric baseline (ablation)Instant NGP NeRF · LLFF 3-viewAverage: 0.118 -> 0.127Hurt
Add foreground loss to photometric loss (ablation)Instant NGP NeRF · DTU all viewsMean Chamfer-L1: 2.87 -> 1.71Improved
Add foreground loss to photometric loss (ablation)Instant NGP NeRF · LLFF 3-viewAverage: 0.210 -> 0.210No clear effect
Add frustum loss (ablation)Photo + foreground loss NeRF · LLFF 3-viewAverage: 0.210 -> 0.135Improved
Add density compactness loss (ablation)Photo + foreground + frustum loss NeRF · LLFF 3-viewAverage: 0.135 -> 0.118Improved
Use 24x24 instead of 48x48 DDM patches (ablation)DiffusioNeRF · LLFF 3-viewAverage: 0.127 -> 0.126Improved
Use 24x24 instead of 48x48 DDM patches (ablation)DiffusioNeRF · DTU 3-viewAverage: 0.135 -> 0.195Hurt
Increase DDM weight to 4x (ablation)24x24-patch DiffusioNeRF · DTU 3-viewAverage: 0.195 -> 0.260Hurt
Do not provide training-image patches to the DDM 25% of the time (ablation)DiffusioNeRF · DTU all viewsMean Chamfer-L1: 1.21 -> 1.91Hurt
Train the DDM on only 20% of Hypersim scenes (ablation)DiffusioNeRF · DTU all viewsMean Chamfer-L1: 1.21 -> 1.65Hurt
Use an RGB-only DDM prior instead of an RGBD prior (ablation)DiffusioNeRF · DTU all viewsMean Chamfer-L1: 1.21 -> 1.31Hurt

Later papers that compared with this method

4 later accepted papers report DiffusioNeRF as a baseline in their results tables; 4 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