RGB-D Salient Object Detection

35 papers with code • 8 benchmarks • 5 datasets

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.

( Image credit: Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks, TNNLS20 )

Greatest papers with code

Uncertainty Inspired RGB-D Saliency Detection

JingZhang617/UCNet 7 Sep 2020

Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution.

RGB-D Salient Object Detection RGB Salient Object Detection +1

UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

JingZhang617/UCNet CVPR 2020

In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process.

RGB-D Salient Object Detection Saliency Detection

RGB-D Salient Object Detection: A Survey

DengPingFan/D3NetBenchmark 1 Aug 2020

Further, considering that the light field can also provide depth maps, we review SOD models and popular benchmark datasets from this domain as well.

RGB-D Salient Object Detection RGB Salient Object Detection +1

Siamese Network for RGB-D Salient Object Detection and Beyond

taozh2017/RGBD-SODsurvey 26 Aug 2020

Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture.

 Ranked #1 on RGB-D Salient Object Detection on SIP (using extra training data)

RGB-D Salient Object Detection Salient Object Detection +1

Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection

jiwei0921/DMRA ICCV 2019

In this work, we propose a novel depth-induced multi-scale recurrent attention network for saliency detection.

Ranked #11 on RGB-D Salient Object Detection on NJU2K (using extra training data)

RGB-D Salient Object Detection Saliency Detection +1

BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network

zyjwuyan/BBS-Net ECCV 2020

In particular, we 1) propose a bifurcated backbone strategy (BBS) to split the multi-level features into teacher and student features, and 2) utilize a depth-enhanced module (DEM) to excavate informative parts of depth cues from the channel and spatial views.

RGB-D Salient Object Detection Salient Object Detection