AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

NerfAcc: Efficient Sampling Accelerates NeRFs

Ruilong Li, Hang Gao, Matthew Tancik, Angjoo Kanazawa

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 130 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 occupancy grid sampling (NerfAcc)NeRF · NeRF-Synthetictraining speedup: 20x speedup, 31.00 -> 31.55 PSNRImproved
add occupancy grid sampling (NerfAcc)TensoRF · Tanks&Templestraining time (min): 18.3 -> 12.6 min, 1.5xImproved
add occupancy grid sampling (NerfAcc)TensoRF · Tanks&TemplesPSNR: 28.13 -> 28.10No clear effect
add occupancy grid sampling (NerfAcc)T-NeRF · D-NeRFPSNR: 28.78 -> 32.22, 20x speedupImproved
add occupancy grid sampling (NerfAcc)BARF · NeRF-Synthetic (perturbed cameras)PSNR: 28.83 -> 30.11, 586 -> 130 minImproved
add occupancy grid sampling (NerfAcc)BARF · NeRF-Synthetic (perturbed cameras)camera rotation error: 0.19 -> 0.07Improved
add occupancy grid sampling (NerfAcc)TiNeuVox · D-NeRFtraining time (min): 11.8 -> 4.2 min, 2.8xImproved
replace proposal estimator with occupancy grid (NerfAcc)K-Planes · D-NeRFtraining time (min): 63.9 -> 38.8 min, 1.6xImproved
use proposal network instead of occupancy grid (ablation)Instant-NGP · Mip-NeRF 360PSNR: 26.41 -> 27.58Improved
use proposal network instead of occupancy grid (ablation)Instant-NGP · NeRF-SyntheticPSNR: 32.55 -> 31.40Hurt
add occupancy grid on top of proposal network (combined sampling) (ablation)Instant-NGP · NeRF-SyntheticPSNR: 31.40 -> 32.35 dB, 5.2 -> 4.3 minImproved
add time-conditioned proposal network instead of occupancy grid (ablation)TiNeuVox · HyperNeRFPSNR: 24.19 -> 24.26No clear effect

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