AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Learning Robust Multi-scale Representation for Neural Radiance Fields from Unposed Images

Nishant Jain, Suryansh Kumar, Luc Van Gool

IJCV 2023 · 3D vision › NeRF and radiance fields · approach: NeRF for scene decomposition and understanding · 11 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
Naively combine Mip-NeRF with BARF pose refinement instead of using RM-NeRFMip-NeRF · Multi-scale Blender Lego (rotation noise)PSNR: 27.01 -> 11.67Hurt
Add joint GNN motion averaging pose refinement to multi-scale NeRF (RM-NeRF vs Mip-NeRF)Mip-NeRF · Multi-scale Blender Lego (rotation noise)PSNR: 21.52 -> 27.01Improved
Initialize RM-NeRF (w/o pose) from the same noisy poses as RM-NeRFRM-NeRF (w/o pose) · Multi-scale Blender Lego (rotation noise)PSNR: 26.34 -> 27.91Improved
Add translation noise to the perturbed posesRM-NeRF · Multi-scale Blender LegoPSNR: 27.01 -> 26.10Hurt
Double the pose noise standard deviationRM-NeRF · Multi-scale Blender Lego (increased noise)PSNR: 26.10 -> 23.21Hurt
Use random pose initialization (w/o pose) instead of noisy COLMAP-style poses under increased noiseRM-NeRF · Multi-scale Blender Lego (increased noise)PSNR: 23.21 -> 26.34Improved
Replace RM-NeRF with RM-NeRF (w/o pose) when both start from COLMAP posesRM-NeRF · Tanks and Temples Truck (same initialization as RM-NeRF)PSNR: 26.12 -> 26.93Improved
Replace RM-NeRF with RM-NeRF (E2E) when both start from COLMAP posesRM-NeRF · Tanks and Temples Truck (same initialization as RM-NeRF)PSNR: 26.12 -> 26.57Improved
Add robust motion averaging and depth priors to random-pose training (RM-NeRF w/o pose vs NoPe-NeRF)NoPe-NeRF · Tanks and Temples Truck (COLMAP intrinsics, random poses)PSNR: 25.28 -> 25.81Improved
Learn intrinsics jointly (RM-NeRF E2E) instead of NeRF-- without COLMAPNeRF-- · Tanks and Temples Truck (no COLMAP poses or intrinsics)PSNR: 24.98 -> 25.12Improved
Add RM-NeRF refinement to COLMAP-pose Mip-NeRFMip-NeRF · Tanks and Temples Truck (COLMAP poses and intrinsics)PSNR: 25.37 -> 26.12Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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