AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

LaRa: Efficient Large-Baseline Radiance Fields

Anpei Chen, Haofei Xu, Stefano Esposito, Siyu Tang, Andreas Geiger

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 45 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
increase number of attention groups from 4 to 8 (ablation)LaRa-fast · GobjaversePSNR: 22.27 -> 23.80Improved
increase number of attention groups from 8 to 16 (ablation)LaRa-fast · GobjaversePSNR: 23.80 -> 25.30Improved
add distortion and normal regularization (ablation)LaRa-fast · GobjaversePSNR: 26.16 -> 25.30 PSNR; GSO geometry Acc 71.2 -> 70.7Mixed
use 2D Gaussian splatting instead of 3D Gaussian splatting (ablation)LaRa-fast · GobjaversePSNR: 26.04 -> 25.30No clear effect
add fine decoding module on top of coarse decoding (ablation)LaRa-fast · GobjaversePSNR: 25.06 -> 25.30Improved
add fine decoding module on top of coarse decoding (ablation)LaRa-fast · GSOLPIPS: 0.1017 -> 0.0683Improved
use spherical harmonics beyond order 0 (ablation)LaRa-fast · GSOLPIPS: 0.0743 -> 0.0683Improved
use Gaussian volume with group attention instead of LGMLaRa · Co3DPSNR: 13.81 -> 21.64Improved
use LaRa vs LGM on GSO LPIPSLaRa · GSOLPIPS: 0.0637 -> 0.0616No clear effect
train 50 epochs instead of 30 epochs (ablation)LaRa · GobjaversePSNR: 25.30 -> 26.14Improved

Later papers that compared with this method

3 later accepted papers report LaRa as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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