IEEE

FreeMask3D: Zero-Shot Point Cloud Instance Segmentation Without 3D Training

Abstract: Point cloud instance segmentation is crucial for 3D scene understanding in robotics. However, existing methods heavily rely on learning-based approaches that require large amounts of ...
IEEE

An Improved Instance Segmentation Method of Visible Occluded Ship Images Based on Residual Feature Fusion Module and Ship Contour Predictor

Abstract: It is significant for harbor management and ship safety to obtain more precise location and shape information from ship instance segmentation. Ships often encounter mutual occlusion during ...
GitHub

SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation

This is the official implementation of paper "SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation". Update (27/05/2025): Our new method, LaSSM, ...
GitHub

Audio-Visual Instance Segmentation

In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in ...