SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.14435 · CVPR · 2023

ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer

Pan Gao, Mingqiang Wei, Shanshan Li, Xiaoyang Tan

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

Problems such as equipment defects or limited viewpoints will lead the captured point clouds to be incomplete. Therefore, recovering the complete point clouds from the partial ones plays an vital role in many practical tasks, and one of the keys lies in the prediction of the missing part. In this paper, we propose a novel point cloud completion approach namely ProxyFormer that divides point clouds into existing (input) and missing (to be predicted) parts and each part communicates information through its proxies. Specifically, we fuse information into point proxy via feature and position extractor, and generate features for missing point proxies from the features of existing point proxies. Then, in order to better perceive the position of missing points, we design a missing part sensitive transformer, which converts random normal distribution into reasonable position information, and uses proxy alignment to refine the missing proxies. It makes the predicted point proxies more sensitive to the features and positions of the missing part, and thus makes these proxies more suitable for subsequent coarse-tofine processes. Experimental results show that our method outperforms state-of-the-art completion networks on several benchmark datasets and has the fastest inference speed.

For agents

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

get_harvested_code_for_paper("2302.14435")
get_code_for_paper("2302.14435")
have("2302.14435")

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

curl https://syntology.ai/api/ran/2302.14435.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.14435.svg)](https://syntology.ai/paper/2302.14435)

Connect an agent — have() is free.