AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

ABLE-NeRF: Attention-Based Rendering With Learnable Embeddings for Neural Radiance Field

Zhe Jun Tang, Tat-Jen Cham, Haiyu Zhao

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Few-shot neural rendering architectures · 14 citations (OpenAlex)

Read the paper

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
Replace physics-based volumetric rendering with masked attention-based ray renderingABLE-NeRF · BlenderPSNR: 33.99 -> 35.02Improved
Replace physics-based volumetric rendering with masked attention-based ray renderingABLE-NeRF · BlenderSSIM: 0.966 -> 0.975Improved
Replace physics-based volumetric rendering with masked attention-based ray renderingABLE-NeRF · BlenderLPIPS: 0.038 -> 0.035Improved
Use ABLE-NeRF instead of Ref-NeRFNeRF rendering on Shiny Blender · Shiny BlenderPSNR: 35.96 -> 33.88Hurt
Use ABLE-NeRF instead of Ref-NeRFNeRF rendering on Shiny Blender · Shiny BlenderSSIM: 0.967 -> 0.969Improved
Use ABLE-NeRF instead of Ref-NeRFNeRF rendering on Shiny Blender · Shiny BlenderLPIPS: 0.058 -> 0.075Hurt
Add Learnable Embeddings (LE) (ablation)ABLE-NeRF · BlenderPSNR: 34.05 -> 35.02Improved
Add Learnable Embeddings (LE) (ablation)ABLE-NeRF · BlenderSSIM: 0.963 -> 0.975Improved
Add Learnable Embeddings (LE) (ablation)ABLE-NeRF · BlenderLPIPS: 0.041 -> 0.035Improved
Mask rear volumes so each volume cannot attend to those behind it (ablation)ABLE-NeRF attention renderer · Novel view synthesissurface rendering accuracyImproved
Append each volume's position on the ray instead of using the masking strategy (ablation)ABLE-NeRF attention renderer · Novel view synthesisrendering accuracyHurt
Add predicted normals (ablation)Ref-NeRF · Shiny BlenderPSNR: 30.91 -> 35.96Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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