AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields

Wenbo Hu, Yuling Wang, Lin Ma, Bangbang Yang, Lin Gao, Xiao Liu, Yuewen Ma

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 145 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 Tri-Mip (mipmap) encoding instead of plain 2D feature maps (ablation)Tri-MipRF · Multi-scale BlenderPSNR (Avg.): 31.48 -> 35.06Improved
add area loss (scale pixel loss by footprint) (ablation)NeRF · Multi-scale BlenderPSNR (Avg.): 27.66 -> 31.23Improved
add 5x super-sampling to hash encodingInstant-ngp · Multi-scale BlenderPSNR (Avg.): 31.20 -> 31.94Improved
add 5x super-sampling to hash encodingInstant-ngp · Multi-scale Blendertraining time: 5 min -> 10 minHurt
use mipmap query (Tri-Mip) vs plain feature maps for reconstruction time (ablation)Tri-MipRF · Multi-scale Blendertraining time: 4.5 min -> 5 minMixed
use Tri-MipRF instead of Instant-ngp on constant-distance capturesInstant-ngp · Single-scale BlenderPSNR: 33.18 -> 33.65Improved
use Tri-Mip encoding (three base-level 2D maps) instead of hash tableInstant-ngp · Single-scale Blendermodel size: 64.1 MB -> 48.2 MBImproved
use Tri-MipRF instead of MipNeRF (explicit hybrid vs implicit)MipNeRF · Multi-scale BlenderPSNR (Avg.): 34.51 -> 35.06Improved

Later papers that compared with this method

3 later accepted papers report Tri-MipRF 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 2 of 2 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