Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks

Deng-Ping Fan, Zheng Lin, Zhao Zhang, Menglong Zhu, Ming-Ming Cheng

Abstract: The use of RGB-D information for salient object detection (SOD) has been extensively explored in recent years. However, relatively few efforts have been put toward modeling SOD in real-world human activity scenes with RGB-D. In this article, we fill the gap by making the following contributions to RGB-D SOD: 1) we carefully collect a new <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> al <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</b> ent <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">P</b> erson (SIP) data set that consists of ~1 K high-resolution images that cover diverse real-world scenes from various viewpoints, poses, occlusions, illuminations, and background s; 2) we conduct a large-scale (and, so far, the most comprehensive) benchmark comparing contemporary methods, which has long been missing in the field and can serve as a baseline for future research, and we systematically summarize 32 popular models and evaluate 18 parts of 32 models on seven data sets containing a total of about 97k images; and 3) we propose a simple general architecture, called deep depth-depurator network (D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> Net). It consists of a depth depurator unit (DDU) and a three-stream feature learning module (FLM), which performs low-quality depth map filtering and cross-modal feature learning, respectively. These components form a nested structure and are elaborately designed to be learned jointly. D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> Net exceeds the performance of any prior contenders across all five metrics under consideration, thus serving as a strong model to advance research in this field. We also demonstrate that D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> Net can be used to efficiently extract salient object masks from real scenes, enabling effective background-changing application with a speed of 65 frames/s on a single GPU. All the saliency maps, our new SIP data set, the D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> Net model, and the evaluation tools are publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/DengPingFan/D3NetBenchmark</uri> .