S-Measure: 93.3Average MAE: 0.021max E-Measure: 96.6max F-Measure: 92.7
Papers with Code · CC BY-SA 4.0
RGB-D Salient Object Detection
RGB-D Salient object detection (SOD) aims at distinguishing the most visually distinctive objects or regions in a scene from the given RGB and Depth data. It has a wide range of applications, including video/image segmentation, object recognition, visual tracking, foreground maps evaluation, image retrieval, content-aware image editing, information discovery, photosynthesis, and weakly supervised semantic segmentation. Here, depth information plays an important complementary role in finding salient objects. Online benchmark: http://dpfan.net/d3netbenchmark.
<span style="color:grey; opacity: 0.6">( Image credit: Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks, TNNLS20 )</span>
논문
S-Measure: 93.1Average MAE: 0.021max E-Measure: 97.1max F-Measure: 92.6
S-Measure: 93.5Average MAE: 0.018max E-Measure: 96.3max F-Measure: 92.5
S-Measure: 87.2Average MAE: 0.038max E-Measure: 92.3max F-Measure: 84.6
S-Measure: 90.8Average MAE: 0.023max F-Measure: 92.8
S-Measure: 92.9Average MAE: 0.022max E-Measure: 96.8max F-Measure: 91.9
S-Measure: 93.6Average MAE: 0.021max E-Measure: 97.5max F-Measure: 92.9
S-Measure: 93.4Average MAE: 0.019