AI Paper Atlas

Research map / 3D vision / 3D generation

ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction

Yixun Liang, Hao He, Ying-Cong Chen

NeurIPS 2023 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 6 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 occlusion transformer to render transformer (ablation)ReTR · DTU sparse viewchamfer distance: 1.31 -> 1.28Improved
add hybrid extractor to render transformer (ablation)ReTR · DTU sparse viewchamfer distance: 1.31 -> 1.29Improved
add both occlusion transformer and hybrid extractor (ablation)ReTR · DTU sparse viewchamfer distance: 1.31 -> 1.17Improved
use continuous positional encoding instead of traditional (ablation)ReTR · DTU sparse view, (64,64) sampleschamfer distance: 1.18 -> 1.17Improved
use continuous positional encoding, (64,0) samples (ablation)ReTR · DTU sparse viewchamfer distance: 1.26 -> 1.22Improved
reduce sample points from (64,64) to (16,16) (ablation)ReTR · DTU sparse viewchamfer distance: 1.17 -> 1.30Hurt
reduce sample points from (64,64) to (16,16) (ablation)VolRecon · DTU sparse viewchamfer distance: 1.38 -> 1.60Hurt
increase coarse sampling to (128,0) (ablation)VolRecon · DTU sparse viewchamfer distance: 1.45 -> 1.79Hurt
remove depth loss for unsupervised training (ablation)ReTR · DTU sparse viewchamfer distance: 1.17 -> 1.45Hurt
remove depth loss (ablation)VolRecon · DTU sparse viewchamfer distance: 1.38 -> 2.06Hurt
remove depth loss (ablation)SparseNeuS · DTU sparse viewchamfer distance: 4.22 -> 1.96Improved
learning-based rendering transformer vs VolRecon volume renderingReTR · DTU sparse viewmean chamfer distance: 1.38 -> 1.17Improved

Later papers that compared with this method

8 later accepted papers report ReTR as a baseline in their results tables; 8 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 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