AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

Yufan Ren, Fangjinhua Wang, Tong Zhang, Marc Pollefeys, Sabine Süsstrunk

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 45 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 the ray transformer to let points attend to other points along the ray (ablation)VolRecon · DTU sparse-view reconstruction (3 views)Chamfer distance: 1.79 -> 1.38Improved
add the global feature volume to provide global shape priors (ablation)VolRecon · DTU sparse-view reconstruction (3 views)Chamfer distance: 1.83 -> 1.38Improved
add depth loss during training (ablation)VolRecon · DTU sparse-view reconstruction (3 views)Chamfer distance: 2.04 -> 1.38Improved
increase the source views from 2 to 3 (ablation)VolRecon · DTU sparse-view reconstructionChamfer distance: 1.72 -> 1.38Improved
increase the source views from 3 to 4 (ablation)VolRecon · DTU sparse-view reconstructionChamfer distance: 1.38 -> 1.35Improved
increase the source views from 4 to 5 (ablation)VolRecon · DTU sparse-view reconstructionChamfer distance: 1.35 -> 1.33Improved
use VolRecon rather than SparseNeuSDTU depth map evaluation · DTUabsolute error (mm): 21.85 -> 7.87Improved
use VolRecon rather than MVSNetDTU depth map evaluation · DTUabsolute error (mm): 13.62 -> 7.87Improved
use VolRecon rather than SparseNeuSDTU full-view reconstruction · DTUChamfer distance: 0.76 -> 0.60Improved
use VolRecon rather than MVSNetDTU full-view reconstruction · DTUChamfer distance: 0.57 -> 0.60Hurt

Later papers that compared with this method

12 later accepted papers report VolRecon as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.

4 more not listed.

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