SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.03480 · 2022

SHRED: 3D Shape Region Decomposition with Learned Local Operations

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

We present SHRED, a method for 3D SHape REgion Decomposition. SHRED takes a 3D point cloud as input and uses learned local operations to produce a segmentation that approximates fine-grained part instances. We endow SHRED with three decomposition operations: splitting regions, fixing the boundaries between regions, and merging regions together. Modules are trained independently and locally, allowing SHRED to generate high-quality segmentations for categories not seen during training. We train and evaluate SHRED with fine-grained segmentations from PartNet; using its merge-threshold hyperparameter, we show that SHRED produces segmentations that better respect ground-truth annotations compared with baseline methods, at any desired decomposition granularity. Finally, we demonstrate that SHRED is useful for downstream applications, out-performing all baselines on zero-shot fine-grained part instance segmentation and few-shot fine-grained semantic segmentation when combined with methods that learn to label shape regions.

For agents

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

get_harvested_code_for_paper("2206.03480")
get_code_for_paper("2206.03480")
have("2206.03480")

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

curl https://syntology.ai/api/ran/2206.03480.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.03480.svg)](https://syntology.ai/paper/2206.03480)

Connect an agent — have() is free.