AI Paper Atlas

Research map / 3D vision / 3D generation

3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching

Runyu Mao, Chen Bai, Yatong An, Fengqing Zhu, Cheng Lu

ECCV 2022 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 23 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 Mutual Query Divergence distillation loss (ablation)Unimodal LoFTR-style student · ScanNet mini (150 scenes) ablationAUC@10deg: 31.47 -> 33.62Improved
add attentive loss on top of MQD (ablation)student · ScanNet mini (150 scenes) ablationAUC@10deg: 33.62 -> 34.77Improved
add MQD loss (ablation)student · ScanNet mini (150 scenes) ablationAUC@5deg: 14.78 -> 16.46Improved
add attentive loss on top of MQD (ablation)student · ScanNet mini (150 scenes) ablationAUC@20deg: 51.70 -> 52.26Improved
add depth modality in teacher (multi-modal teacher) (ablation)unimodal model · ScanNet mini (150 scenes) ablationAUC@10deg: 31.47 -> 36.53Improved
distill from multi-modal teacher (full student vs LoFTR)LoFTR · ScanNet indoor poseAUC@10deg: 40.80 -> 43.60Improved
distill from multi-modal teacher (full student vs LoFTR)LoFTR · MegaDepth outdoor poseAUC@10deg: 67.11 -> 68.46Improved
distill from multi-modal teacherLoFTR · HPatches homographyAUC@5px: 71.9 -> 73.1Improved
distill from multi-modal teacherLoFTR · HPatches homographyAUC@10px: 79.9 -> 81.0Improved
train slim model (half coarse layers) with teacher distillation (ablation)Slim Model · ScanNet mini (150 scenes) model compressionAUC@10deg: 29.68 -> 31.76Improved
train slim model with teacher distillation vs full-size model (ablation)Full-Size Model · ScanNet mini (150 scenes) model compressionAUC@20deg: 48.44 -> 49.51Improved
halve coarse transformer layers (4 to 2) without distillation (ablation)Full-Size Model · ScanNet mini (150 scenes) model compressionAUC@10deg: 31.47 -> 29.68Hurt

Later papers that compared with this method

1 later accepted paper reports 3DG-STFM as a baseline in their results tables; 0 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