3D Dense Shape Correspondence
8 papers with code • 1 benchmarks • 2 datasets
Finding a meaningful correspondence between two or more shapes is one of the most fundamental shape analysis tasks. The problem can be generally stated as: given input shapes S1,S2,...,SN, find a meaningful relation (or mapping) between their elements. Under different contexts, the problem has also been referred to as registration, alignment, or simply, matching. Shape correspondence is a key algorithmic component in tasks such as 3D scan alignment and space-time reconstruction, as well as an indispensable prerequisite in diverse applications including attribute transfer, shape interpolation, and statistical modeling.
Benchmarks
These leaderboards are used to track progress in 3D Dense Shape Correspondence
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
SHREC'19
TOSCA
Most implemented papers
Learning elementary structures for 3D shape generation and matching
TheoDEPRELLE/AtlasNetV2
•
•
NeurIPS 2019
We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape.
Correspondence Learning via Linearly-invariant Embedding
riccardomarin/Diff-FMaps
•
•
NeurIPS 2020
However, instead of using the Laplace-Beltrami eigenfunctions as done in virtually all previous works in this domain, we demonstrate that learning the basis from data can both improve robustness and lead to better accuracy in challenging settings.
3D-CODED : 3D Correspondences by Deep Deformation
By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template.
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
ZENGYIMING-EAMON/CorrNet3D
•
•
CVPR 2021
The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence.
DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
dvirginz/dpc
•
•
We present a new method for real-time non-rigid dense correspondence between point clouds based on structured shape construction.
ROCA: Robust CAD Model Retrieval and Alignment from a Single Image
We present ROCA, a novel end-to-end approach that retrieves and aligns 3D CAD models from a shape database to a single input image.
SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence
openspaceai/se-ornet
•
•
CVPR 2023
The key of our approach is to exploit an orientation estimation module with a domain adaptive discriminator to align the orientations of point cloud pairs, which significantly alleviates the mispredictions of symmetrical parts.
Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features
niladridutt/Diffusion-3D-Features
•
•
We present Diff3F as a simple, robust, and class-agnostic feature descriptor that can be computed for untextured input shapes (meshes or point clouds).
