SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.05906 · ECCV · 2024

PartSTAD: 2D-to-3D Part Segmentation Task Adaptation

Hyunjin Kim, Minhyuk Sung

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

Stapler {body, lid} Display {base, screen, support} Chair {arm, back, leg, seat, wheel} Camera {button, lens} Bucket {handle} Dispenser {head, lid} Clock {hand} Kettle {lid, handle, spout} Dispenser {spout, switch} Scissors {blade, handle, screw} Switch {button} StorageFurniture {door, drawer, handle} Weighted Merging Figure 1: We introduce PartSTAD, a novel few-shot 3D point cloud part segmentation method that leverages 2D-to-3D task adaptation. By obtaining 2D segmentation masks in multi-view images from GLIP [25] and SAM [20] and optimizing the mask weights for 3D segmentation as a learning objective, it can successfully predict finegrained parts with accurate boundaries, as shown in the figure above.

For agents

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

get_harvested_code_for_paper("2401.05906")
get_code_for_paper("2401.05906")
have("2401.05906")

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

curl https://syntology.ai/api/ran/2401.05906.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.05906.svg)](https://syntology.ai/paper/2401.05906)

Connect an agent — have() is free.