AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields

Anh-Quan Cao, Raoul de Charette

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 58 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 reprojection loss for explicit depth optimization (ablation)SceneRF · SemanticKITTI novel depthdelta1: 69.10 -> 75.07Improved
add reprojection loss for explicit depth optimization (ablation)SceneRF · BundleFusion novel depthdelta1: 64.99 -> 72.71Improved
add reprojection loss to other NeRFsVisionNeRF · SemanticKITTI novel depthdelta1: 69.11 -> 75.77Improved
add probabilistic ray sampling (PrSamp) (ablation)SceneRF · SemanticKITTI novel depthdelta1: 71.85 -> 75.07Improved
add Spherical U-Net decoder (ablation)SceneRF · BundleFusion novel depthdelta1: 59.77 -> 72.71Improved
add RGB loss alongside reprojection loss (ablation)SceneRF · SemanticKITTI novel depthdelta1: 72.15 -> 75.07Improved
add depth components (reproj, PrSamp, SU-Net) on novel view synthesis (ablation)SceneRF · SemanticKITTI novel viewLPIPS: 0.464 -> 0.476 (w/o SU-Net vs full)Mixed
increase number of Gaussians or points per Gaussian beyond k=4, m=8 (ablation)PrSamp · SemanticKITTI novel depthdelta1: 75.01 -> 74.59 (k=8, m=8)No clear effect
replace PrSamp with MipNeRF360 sampling (ablation)SceneRF · SemanticKITTI and BundleFusion novel depthdelta1/delta2/delta3: -6/-3/-2 on SemanticKITTIHurt
add fused novel depth views reconstruction scheme (ablation)SceneRF · BundleFusion scene reconstructionIoU: 17.33 -> 20.16Improved
use self-supervised image supervision instead of depth supervision for scene reconstructionSceneRF vs MonoScene (depth) · SemanticKITTI scene reconstructionIoU: 13.53 -> 13.84Improved
use spherical 120-degree decoder instead of planar decoders (ablation)SU-Net · SemanticKITTI novel depthdelta1: 73.78 -> 75.01Improved

Later papers that compared with this method

3 later accepted papers report SceneRF as a baseline in their results tables; 3 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