AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Mega-NERF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs

Haithem Turki, Deva Ramanan, Mahadev Satyanarayanan

CVPR 2022 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 410 citations (OpenAlex)

Check 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
Use spatially partitioned NeRF submodules with geometry-aware pixel assignmentMega-NeRF · Mill 19 - RubblePSNRImproved
Add per-image appearance embeddings (ablation)Mega-NeRF · Mill 19, Quad 6k, UrbanScene3DPSNR: 20.42 -> 22.34; 16.16 -> 18.08; 19.45 -> 23.60Improved
Use ellipsoid foreground bounds and altitude-based ray limits instead of NeRF++ unit-sphere bounds (ablation)Mega-NeRF · Mill 19, Quad 6k, UrbanScene3DPSNR: 22.14 -> 22.34; 18.02 -> 18.08; 23.42 -> 23.60Improved
Use spatially-aware sparse connections instead of fully connected layers (ablation)Mega-NeRF · Mill 19, UrbanScene3DPSNR: 21.63 -> 22.34; 22.44 -> 23.60Improved
Train submodules on their respective pixel partitions instead of jointly on the full dataset (ablation)Mega-NeRF · Mill 19, Quad 6k, UrbanScene3DPSNR: 21.10 -> 22.34; 17.43 -> 18.08; 21.45 -> 23.60Improved
Prune pixel assignments using estimated ray intersections with surfaces (ablation)Mega-NeRF · Mill 19, Quad 6k, UrbanScene3DPSNR: 22.50 -> 22.76; 18.13 -> 18.16; 23.65 -> 23.87Improved
Increase the number of submodules from 1 to 16 at fixed channel count (ablation)Mega-NeRF · Mill 19 - RubblePSNR: 21.75 -> 23.34; 22.60 -> 24.52; 23.40 -> 25.68Improved
Increase channels per submodule from 128 to 512 (ablation)Mega-NeRF · Mill 19 - RubblePSNR: 21.75 -> 23.40; 22.61 -> 24.53; 23.08 -> 25.11; 23.34 -> 25.68Improved
Use Mega-NeRF-Dynamic temporal-coherence rendering instead of conventional full ray samplingMega-NeRF · Mill 19, Quad 6k, UrbanScene3Drender time (s): 101 -> 3.96; 174 -> 2.91; 122 -> 3.219Improved

Later papers that compared with this method

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

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