HyperSeg: Towards Universal Visual Segmentation with Large Language Model

TL;DR

HyperSeg is a novel VLLM-based universal segmentation model capable of handling both image and video perception tasks, including complex reasoning, by integrating hybrid recognition modules and temporal understanding.

Contribution

It introduces HyperSeg, the first universal segmentation model leveraging VLLMs for pixel-level perception across images and videos with reasoning capabilities.

Findings

Effective in universal image and video segmentation tasks

Handles complex reasoning perception tasks

Outperforms existing methods in accuracy

Abstract

This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs). Despite significant progress in current unified segmentation methods, limitations in adaptation to both image and video scenarios, as well as the complex reasoning segmentation, make it difficult for them to handle various challenging instructions and achieve an accurate understanding of fine-grained vision-language correlations. We propose HyperSeg, the first VLLM-based universal segmentation model for pixel-level image and video perception, encompassing generic segmentation tasks and more complex reasoning perception tasks requiring powerful reasoning abilities and world knowledge. Besides, to fully leverage the recognition capabilities of VLLMs and the fine-grained visual information, HyperSeg incorporates hybrid entity recognition and fine-grained visual perceiver modules for various segmentation tasks. Combined with the temporal adapter, HyperSeg achieves a comprehensive understanding of temporal information. Experimental results validate the effectiveness of our insights in resolving universal image and video segmentation tasks, including the more complex reasoning perception tasks. Our code is available.