SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.01558 · 2022

PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models

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

Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets with fine-grained part annotations, which are costly to collect. This paper explores an alternative way for low-shot part segmentation of 3D point clouds by leveraging a pretrained image-language model, GLIP, which achieves superior performance on open-vocabulary 2D detection. We transfer the rich knowledge from 2D to 3D through GLIP-based part detection on point cloud rendering and a novel 2D-to-3D label lifting algorithm. We also utilize multi-view 3D priors and few-shot prompt tuning to boost performance significantly. Extensive evaluation on PartNet and PartNet-Mobility datasets shows that our method enables excellent zero-shot 3D part segmentation. Our few-shot version not only outperforms existing few-shot approaches by a large margin but also achieves highly competitive results compared to the fully supervised counterpart. Furthermore, we demonstrate that our method can be directly applied to iPhone-scanned point clouds without significant domain gaps.

For agents

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

get_harvested_code_for_paper("2212.01558")
get_code_for_paper("2212.01558")
have("2212.01558")

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

curl https://syntology.ai/api/ran/2212.01558.json

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

[![Syntology run record](https://syntology.ai/api/ran/2212.01558.svg)](https://syntology.ai/paper/2212.01558)

Connect an agent — have() is free.