AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

RING-NeRF : Rethinking Inductive Biases for Versatile and Efficient Neural Fields

Doriand Petit, Steve Bourgeois, Dumitru Pavel, Vincent Gay-Bellile, Florian Chabot, Loïc Barthe

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 1 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 RING-NeRF architecture (summed residual multi-scale grids) over Nerfacto concatenated grids (ablation)Nerfacto · Mip-NeRF 360 (mono-scale, full res)PSNR: 27.09 -> 27.65Improved
add distance-aware forward mapping (cone casting LOD selection) (ablation)RING-NeRF · Mip-NeRF 360 (mono-scale, full res)PSNR: 27.65 -> 28.26Improved
add continuous coarse-to-fine optimization on stable NVS setup (ablation)RING-NeRF · Mip-NeRF 360 (mono-scale, full res)PSNR: 28.26 -> 28.09No clear effect
add continuous coarse-to-fine instead of discrete (ablation)RING-NeRF · DTU few-view (3 images)PSNR: 15.79 -> 16.18Improved
add FreeNeRF density loss on few views (ablation)RING-NeRF · DTU few-view (3 images)PSNR: 10.56 -> 14.58Improved
add coarse-to-fine with density loss on few views (ablation)RING-NeRF · DTU few-view (3 images)PSNR: 14.58 -> 16.18Improved
RING-NeRF architecture instead of Nerfacto with progressive grids (Nerfacto+)Nerfacto+ · DTU few-view (3 images)PSNR: 13.61 -> 16.18Improved
use RING-NeRF for SDF reconstruction without scene-specific initializationNeuS-facto · Replica SDF without initializationChamfer-L1 (cm): 17.61 -> 5.71Improved
RING-NeRF versus per-LOD or super-sampling anti-aliasing methods for training timeRING-NeRF · Mip-NeRF 360training time (hours): 1.10h -> 0.45hImproved
RING-NeRF versus FreeNeRF on quality in few-view settingRING-NeRF · DTU few-view (3 images)PSNR: 19.92 -> 16.18Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 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