AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

DINER: Depth-Aware Image-Based NEural Radiance Fields

Malte Prinzler, Otmar Hilliges, Justus Thies

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 29 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
Use DINER instead of pixelNeRFImage-based NeRF · FaceScapeLPIPS: 0.165 -> 0.099Improved
Use DINER instead of pixelNeRFImage-based NeRF · DTULPIPS: 0.38 -> 0.23Improved
Add depth awareness (ablation)pixelNeRF · FaceScapeLPIPS: 0.16 -> 0.15Improved
Add perceptual loss (ablation)Depth-aware pixelNeRF · FaceScapeLPIPS: 0.15 -> 0.11Improved
Add perceptual loss (ablation)DINER · FaceScapePSNR: 24.40 -> 22.42Hurt
Add source feature extrapolation (ablation)DINER with perceptual loss · FaceScapeLPIPS: 0.11 -> 0.11No clear effect
Add anti-bias loss (ablation)DINER with source feature extrapolation · FaceScapeL1: 0.029 -> 0.022Improved
Add depth-guided sampling (ablation)DINER with anti-bias loss · FaceScapeLPIPS: 0.11 -> 0.12Hurt
Increase batch size after reducing samples per ray with depth-guided sampling (ablation)DINER · FaceScapeLPIPS: 0.12 -> 0.10Improved
Improve depth accuracy (ablation)DINER · FaceScapeSynthesis qualityImproved
Use depth-guided instead of coarse-to-fine sampling with 40 samples per ray (ablation)DINER sampling · FaceScapeMedian Chamfer distance: 6.4 mm -> 0.28 mmImproved
Add perceptual loss (ablation)DINER · DTULPIPS: 0.27 -> 0.23Improved

Later papers that compared with this method

2 later accepted papers report DINER as a baseline in their results tables; 2 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