Home Console Docs News Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

3D Dense Shape Correspondence On Shrec 19

Metrics

Accuracy at 1%

Euclidean Mean Error (EME)

Results

Performance results of various models on this benchmark

			Paper Title	Repository
Diffusion 3D Features (Zero-shot)	26.4	1.7	Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features
TANet (Trained on Surreal)	21.5	4.5	Unsupervised Template-assisted Point Cloud Shape Correspondence Network	-
SE-ORNet (Trained on Surreal)	21.5	4.6	SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence
DPC (Trained on Surreal)	17.7	6.1	DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
SE-ORNet	17.5	5.1	SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence
DPC	15.3	5.6	DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
CorrNet3D (Trained on Surreal)	6.0	6.9	CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
Diff-FMaps (Trained on Surreal)	4.0	7.1	Correspondence Learning via Linearly-invariant Embedding
Elementery Structures(Trained on Surreal)	2.3	7.6	Learning elementary structures for 3D shape generation and matching
3DCODED (Trained on Surreal)	2.1	8.1	3D-CODED : 3D Correspondences by Deep Deformation
CorrNet3D	0.4	33.8	CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

0 of 11 row(s) selected.

3D Dense Shape Correspondence On Shrec 19 | SOTA | HyperAI