Abstract: Point cloud rigid registration is a fundamental problem in 3D computer vision. In the multiview case ... we transpose the registration problem into the latent space of a pretrained ...

It’s built around a simple PointNet-style autoencoder trained on partial point clouds from ShapeNet. I’ve always found it fascinating how models can "fill in the blanks," whether it’s with text, ...

"I’d say that abstract expression represents a kind of freedom for me, and likewise, for the audience, there's freedom in how ...

and geometric distortions in the 3D point cloud. This paper proposes a novel 3D keypoint detection method based on point cloud structural saliency (PCSS) to realize stable and efficient 3D keypoint ...

Official implementation of 'GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model'. The paper has been accepted by ICML 2025. Pre-trained 3D vision models have gained significant attention ...

Get article recommendations from ACS based on references in your Mendeley library. Pair your accounts.