SOTAVerified

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.

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

Papers

Showing 125 of 88 papers

TitleStatusHype
DFormer: Rethinking RGBD Representation Learning for Semantic SegmentationCode2
Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff PerspectiveCode1
MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object DetectionCode1
CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object DetectionCode1
Mutual Information Regularization for Weakly-supervised RGB-D Salient Object DetectionCode1
Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object DetectionCode1
SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object DetectionCode1
Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency DetectionCode1
An Energy-Based Prior for Generative SaliencyCode1
Joint Learning of Salient Object Detection, Depth Estimation and Contour ExtractionCode1
CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object DetectionCode1
MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion AttentionCode1
TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding NetworkCode1
Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object DetectionCode1
Calibrated RGB-D Salient Object DetectionCode1
Visual Saliency TransformerCode1
BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object DetectionCode1
Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal FusionCode1
Densely Deformable Efficient Salient Object Detection NetworkCode1
Self-Supervised Pretraining for RGB-D Salient Object DetectionCode1
RGB-D Salient Object Detection via 3D Convolutional Neural NetworksCode1
Learning Selective Mutual Attention and Contrast for RGB-D Saliency DetectionCode1
Uncertainty Inspired RGB-D Saliency DetectionCode1
Siamese Network for RGB-D Salient Object Detection and BeyondCode1
Progressively Guided Alternate Refinement Network for RGB-D Salient Object DetectionCode1
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.