AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

NeRF-XL: NeRF at Any Scale with Multi-GPU

Ruilong Li, Sanja Fidler, Angjoo Kanazawa, Francis Williams

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF

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
train jointly with non-overlapping NeRFs instead of independent overlapped NeRFsNeRF-XL · Garden, Building, University4, MatrixCity (1x to 16x GPUs)PSNR and rays per secondImproved
rewrite volume rendering as partition-based tile composition to cut communication (ablation)NeRF-XL · University4multi-GPU communication cost: reduction over 2x vs sample-based synchronizationImproved
distribute parameters across GPUs (NeRF-XL) instead of distributing rays (PyTorch DDP)NeRF-XL · University4PSNRImproved
distribute parameters across GPUs instead of rays (DDP)NeRF-XL · University4rendering speedHurt
joint training with synchronization versus independent trainingNeRF-XL · training speedtraining time: 1x-1.5x slower than independent trainingHurt
increase GPUs and parameters with joint trainingNeRF-XL · MatrixCity, Laguna Seca, Mexico Beachvisual qualityImproved

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