This repository serves as a curated collection of papers and code for deep learning-based salient object detection (SOD) across various modalities, including 2D RGB, 3D RGB-D/T, video, and 4D light fields. It aims to provide researchers and practitioners with a comprehensive overview and access to state-of-the-art methods in the field.

How It Works

The project organizes and links to research papers and their corresponding code implementations, categorized by modality and publication year. It covers a wide range of techniques, from early methods to recent advancements, facilitating a structured understanding of the evolution and current landscape of SOD research.

Quick Start & Requirements

This repository is a curated list and does not have a direct installation or execution command. Users are directed to individual paper links for code and dataset downloads.

Highlighted Details

• Comprehensive coverage of 2D, 3D (RGB-D/T), 4D Light Field, and Video Salient Object Detection.
• Includes links to datasets, evaluation metrics, and leaderboards for benchmarking.
• Regularly updated with recent AAAI, CVPR, ECCV, NeurIPS, and PAMI publications.
• Provides access to code for a vast number of SOD methods.

Maintenance & Community

The repository is maintained by jiwei0921 and acknowledges contributions from Deng-Ping Fan and Tao Zhou. It appears to be actively updated with new papers.

Licensing & Compatibility

The repository itself does not specify a license. Individual code repositories linked within will have their own licenses, which may vary and could include restrictions on commercial use.

Limitations & Caveats

This is a curated list of papers and code, not a unified framework. Users must navigate to individual paper links to access code and datasets, which may have varying dependencies and setup requirements. The quality and maintenance of linked code are not guaranteed by this repository.