SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.14376 · 2023

ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understanding

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recently, a growing number of work design unsupervised paradigms for point cloud processing to alleviate the limitation of expensive manual annotation and poor transferability of supervised methods. Among them, CrossPoint follows the contrastive learning framework and exploits image and point cloud data for unsupervised point cloud understanding. Although the promising performance is presented, the unbalanced architecture makes it unnecessarily complex and inefficient. For example, the image branch in CrossPoint is $\sim$8.3x heavier than the point cloud branch leading to higher complexity and latency. To address this problem, in this paper, we propose a lightweight Vision-and-Pointcloud Transformer (ViPFormer) to unify image and point cloud processing in a single architecture. ViPFormer learns in an unsupervised manner by optimizing intra-modal and cross-modal contrastive objectives. Then the pretrained model is transferred to various downstream tasks, including 3D shape classification and semantic segmentation. Experiments on different datasets show ViPFormer surpasses previous state-of-the-art unsupervised methods with higher accuracy, lower model complexity and runtime latency. Finally, the effectiveness of each component in ViPFormer is validated by extensive ablation studies. The implementation of the proposed method is available at https://github.com/auniquesun/ViPFormer.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.14376")
get_code_for_paper("2303.14376")
have("2303.14376")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.14376.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.14376.svg)](https://syntology.ai/paper/2303.14376)

Connect an agent — have() is free.