AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Digging into Radiance Grid for Real-Time View Synthesis with Detail Preservation

Jian Zhang, Jinchi Huang, Bowen Cai, Huan Fu, Mingming Gong, Chaohui Wang, Jiaming Wang, Hongchen Luo, Rongfei Jia, Binqiang Zhao, Xing Tang

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 9 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 perceptual loss Lp (ablation)HrSRG · Real 360 Objects "Hat"LPIPS: 0.061 -> 0.056Improved
add perceptual loss Lp (ablation)HrSRG · Real 360 Objects "Hat"PSNR: 26.43 -> 26.64Improved
add specular MLP (vs diffuse HrSRG-minus) (ablation)HrSRG · Real 360 Objects "Hat"LPIPS: 0.069 -> 0.056Improved
add specular MLP (vs diffuse HrSRG-minus) (ablation)HrSRG · Real 360 Objects "Hat"PSNR: 25.65 -> 26.64Improved
use 512^3 voxel grid instead of 256^3 (ablation)HrSRG · Real 360 Objects "Hat"LPIPS: 0.107 -> 0.056Improved
directly optimize voxel colors instead of converged Def-NeRF (ablation)HrSRG vs Def-NeRF-Plus · Real 360 Objects "Hat"LPIPS: 0.128 -> 0.056Improved
apply median cut pruning (ablation)HrSRG · Synthetic-NeRF 800x800model size (MB): 210.4 -> 35.8Improved
apply median cut pruning (ablation)HrSRG · Synthetic-NeRF 800x800PSNR: 31.06 -> 31.04No clear effect
raise threshold tau1 from 0.01 to 0.9 (ablation)HrSRG · Shoemodel size: 169.4M -> 35.5MNo clear effect
use HrSRG instead of PlenOctreeHrSRG vs PlenOctree · Tanks and TemplesLPIPS: 0.131 -> 0.099Improved
use HrSRG instead of PlenOctreeHrSRG vs PlenOctree · Tanks and TemplesPSNR: 27.99 -> 27.33Hurt
use HrSRG instead of PlenOctree-512HrSRG vs PlenOctree · Synthetic-NeRF 800x800PSNR: 31.67 -> 31.04Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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