Superpoint Transformer (SPT) is a superpoint-based transformer architecture that efficiently performs semantic segmentation on large-scale 3D scenes. Install.sh · Issues 2 · Pull requests 1

13 июн. 2023 г. · We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes.

Our proposed method Superpoint Transformer. (SPT) achieves state-of-the-art with a reduction of up to 200- fold in model size and 70-fold in training time (in ...

This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry ...

This tutorial will demonstrate how to use Superpoint Transformer (SPT) on your own point cloud data.

SuperPoint Transformer proposes a new framework for 3D semantic segmentation tasks. It leverages transformers and incorporates superpoints.

28 нояб. 2022 г. · This paper proposes a novel end-to-end 3D instance segmentation method based on Superpoint Transformer, named as SPFormer.

It groups potential features from point clouds into superpoints, and directly predicts instances through query vectors with- out relying on the results of ...

Продолжительность: 59:10
Опубликовано: 10 июл. 2024 г.

We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes.