computer-vision-5

Weakly Supervised 3D Point Cloud Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in weakly-supervised-3d-point-cloud-segmentation-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find weakly-supervised-3d-point-cloud-segmentation-5 models and implementations

Datasets

ScribbleKITTI

Subtasks

No subtasks available.

Most implemented papers

Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision

Guosheng Lin, S. Dong, Ruibo Li, Jiacheng Wei, Fayao Liu•Tue Aug 09 2022

A Cross-graph Competing Random Walks (CRW) algorithm that encourages competition among different instance graphs to resolve ambiguities in closely placed objects, improving instance assignment accuracy.

4

Content

0

Paper Graph

COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation

Raoul de Charette, Anh-Quan Cao, Rong Li•Mon Oct 03 2022

COARSE3D is proposed, a novel architecture-agnostic contrastive learning strategy for 3D segmentation that leverages a prototype memory bank capturing class-wise global dataset information efficiently into a small number of prototypes acting as keys.

17 0

Paper Graph

Adding a benchmark result helps the community track progress.