AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

MixNeRF: Modeling a Ray With Mixture Density for Novel View Synthesis From Sparse Inputs

Seunghyeon Seo, Donghoon Han, Yeonjin Chang, Nojun Kwak

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Few-shot neural rendering architectures · 37 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
Model colors along ray samples with a mixture density model (ablation)MixNeRF · Sparse-view novel view synthesisrendering qualityImproved
Add auxiliary ray-depth estimation (ablation)MixNeRF with mixture density modeling · Sparse-view novel view synthesisrendering qualityImproved
Add regenerated blending weights without ray-depth supervision (ablation)MixNeRF · Sparse-view novel view synthesisrendering qualityNo clear effect
Add regenerated blending weights based on estimated ray depth (ablation)MixNeRF with ray-depth supervision · Sparse-view novel view synthesisrendering qualityImproved
Reduce ray samples from 128 to 32 (ablation)MixNeRF · LLFF 3-viewSSIM: 0.629 -> 0.620Hurt
Use 32 rather than 128 ray samplesMixNeRF versus RegNeRF · LLFF 3-viewSSIM: 0.576 -> 0.620Improved
Use 16 rather than 128 ray samples (ablation)MixNeRF · LLFF 3-viewSSIM: 0.629 -> 0.580Hurt
Use mixture-density modeling instead of RegNeRF's approachMixNeRF versus RegNeRF · LLFF 3-viewPSNR: 19.08 -> 19.27Improved
Use mixture-density modeling instead of RegNeRF's approachMixNeRF versus RegNeRF · Realistic Synthetic 360° 4-viewPSNR: 13.71 -> 18.99Improved

Later papers that compared with this method

3 later accepted papers report MixNeRF 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 1 of 1 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