AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

Norman Müller, Yawar Siddiqui, Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder, Matthias Nießner

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Few-shot neural rendering architectures · 127 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 2D rendering supervision (ablation)DiffRF · PhotoShape ChairsFID: 18.27 -> 15.95Improved
Add 2D rendering supervision (ablation)DiffRF · PhotoShape ChairsKID: 9.263 -> 7.935Improved
Add 2D rendering supervision (ablation)DiffRF · PhotoShape ChairsCOV: 59.20 -> 58.93Hurt
Add 2D rendering supervision (ablation)DiffRF · PhotoShape ChairsMMD: 4.543 -> 4.416Improved
Add 2D rendering supervision (ablation)DiffRF · ABO TablesFID: 35.89 -> 27.06Improved
Add 2D rendering supervision (ablation)DiffRF · ABO TablesKID: 13.94 -> 10.03Improved
Add 2D rendering supervision (ablation)DiffRF · ABO TablesCOV: 63.46 -> 61.54Hurt
Add 2D rendering supervision (ablation)DiffRF · ABO TablesMMD: 8.013 -> 7.610Improved
Use DiffRF rather than EG3D for unconditional synthesisPhotoShape Chairs · PhotoShape ChairsFID: 16.54 -> 15.95Improved
Use DiffRF rather than EG3D for unconditional synthesisABO Tables · ABO TablesFID: 31.18 -> 27.06Improved
Use DiffRF rather than EG3D for masked completionPhotoShape Chairs · PhotoShape Chairs masked completion (Avg)mPSNR: 24.82 -> 27.53Improved
Use DiffRF rather than EG3D for masked completionPhotoShape Chairs · PhotoShape Chairs masked completion (Avg)FID: 30.67 -> 27.78Improved

Later papers that compared with this method

7 later accepted papers report DiffRF as a baseline in their results tables; 7 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