AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

CVPR 2022 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 98 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 recurrent neural volume fusion instead of IBRNet direct inferenceScanNet novel-view synthesis · ScanNetPSNR: 21.19 -> 22.99Helped
Fine-tune the predicted radiance field per scene for 1hNeRFusion · ScanNetPSNR: 22.99 -> 26.49Helped
Fine-tune the predicted radiance field per scene for 1hNeRFusion · NeRF SyntheticPSNR: 25.47 -> 31.25Helped
Fine-tune the predicted radiance field per scene for 1hNeRFusion · DTUPSNR: 26.19 -> 31.79Helped
Use recurrent neural volume fusion instead of IBRNet direct inferenceNeRFusion · NeRF SyntheticSSIM: 0.916 -> 0.922Helped
Use recurrent neural volume fusion instead of IBRNet direct inferenceNeRFusion · NeRF SyntheticPSNR: 25.51 -> 25.47No clear effect
Use recurrent neural volume fusion instead of MVSNeRF direct inferenceNeRFusion · DTUPSNR: 26.63 -> 26.19Hurt
Increase the number of input neighboring views (ablation)NeRFusion local volume reconstruction · Novel-view renderingrendered detailHelped

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