IEEE

Deformation-Resilient Multigranularity Learning for Unaligned RGB–T Semantic Segmentation

Abstract: RGB–Thermal semantic segmentation (SS) aims to combine visual light and thermal images to determine the semantic category for each pixel and create an object mask. While existing methods ...
GitHub

Easy integration of Ilastik segmentation models in Python.

This package provides seamless integration of pre-trained image segmentation models from Ilastik into Python workflows, empowering users with efficient and intuitive image segmentation capabilities ...
GitHub

ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

Novel Framework: First segmentation paradigm built on a unified multimodal understanding-generation architecture, eliminating task-specific modules. SOTA without Extra Heads: Demonstrates unified ...
IEEE

HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation

Abstract: Semantic perception in driving scenarios plays a crucial role in intelligent transportation systems. However, existing Transformer-based semantic segmentation methods often do not fully ...