AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Neural Radiance Field Codebooks

Matthew Wallingford, Aditya Kusupati, Alex Fang, Vivek Ramanujan, Aniruddha Kembhavi, Roozbeh Mottaghi, Ali Farhadi

ICLR 2023 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 0 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 NRC rather than ObSuRF for unsupervised segmentationNRC · ProcTHORARI: .228 -> .295Improved
Use NRC rather than ObSuRF for unsupervised segmentationNRC · NYU DepthARI: .141 -> .182Improved
Use NRC rather than ObSuRF for unsupervised segmentationNRC · CLEVR-3DFG-ARI: .978 -> .977Hurt
Use NRC instead of the strongest baseline representationObject navigation policy · RoboTHOR object navigation testSuccess Rate (%): 47.0 -> 50.1Improved
Use NRC instead of the strongest baseline representationObject navigation policy · RoboTHOR object navigation testSPL: .200 -> .239Improved
Use NRC rather than ObSuRFDepth ordering · ProcTHOR testDepth Order Acc. (%): 18.3 -> 23.8Improved
Add intra-code variation modeling (ablation)NRC with fixed codebook size · ProcTHORARI: .182 -> .284Improved
Learn codebook size (ablation)NRC without variation module · ProcTHORARI: .182 -> .197Improved
Learn codebook size in addition to intra-code variation (ablation)NRC · ProcTHORARI: .284 -> .295Improved
Vary fixed codebook size (ablation)NRC without learned code count · ProcTHORARI: 10: .247; 20: .256; 30: .266; 40: .279; 50: .286; 60: .293; 70: .288; 80: .295; 90: .279; 100: .273Mixed
Use NRC rather than ObSuRF on cluttered scenesUnsupervised segmentation · NYU Depth (Hard)ARI: .092 -> .139Improved
Use NRC rather than ObSuRFUnsupervised segmentation · MatterPort3DARI: .178 -> .237Improved

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