RGB-D Salient Object Detection

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-25.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

5 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 61 papers with code (88 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• RGB-D Salient Object Detection: A Survey
  1 Aug 2020 9 repositories listed
  Further, considering that the light field can also provide depth maps, we review SOD models and popular benchmark datasets from this domain as well.
• Uncertainty Inspired RGB-D Saliency Detection
  7 Sep 2020 4 repositories listed
  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…
• CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection
  6 Oct 2022 3 repositories listed
  Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the…
• Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection
  17 Aug 2023 2 repositories listed
  By integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved.
• Visual Saliency Transformer
  25 Apr 2021 2 repositories listed Syntology ran 7 of 11 samples · 4 unverified · 11 pointer-only (licence)
  We also develop a token-based multi-task decoder to simultaneously perform saliency and boundary detection by introducing task-related tokens and a novel patch-task-attention mechanism.
• Siamese Network for RGB-D Salient Object Detection and Beyond
  26 Aug 2020 2 repositories listed
  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…
• Accurate RGB-D Salient Object Detection via Collaborative Learning
  23 Jul 2020 2 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  The explicitly extracted edge information goes together with saliency to give more emphasis to the salient regions and object boundaries.
• Cross-Modal Weighting Network for RGB-D Salient Object Detection
  9 Jul 2020 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  In this paper, we propose a novel Cross-Modal Weighting (CMW) strategy to encourage comprehensive interactions between RGB and depth channels for RGB-D SOD.
• Bifurcated backbone strategy for RGB-D salient object detection
  6 Jul 2020 2 repositories listed Syntology ran 3 of 5 samples · 2 unverified
  In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS).
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
  15 Jul 2019 2 repositories listed
  The use of RGB-D information for salient object detection has been extensively explored in recent years.
• Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection
  1 Jun 2019 2 repositories listed
  The large availability of depth sensors provides valuable complementary information for salient object detection (SOD) in RGBD images.
• PDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detection
  23 Mar 2018 2 repositories listed
  One is the lack of tremendous amount of annotated data to train a network.
• Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspective
  7 May 2025 1 repository listed
  To balance the efficiency and performance, we propose a Speed-Accuracy Tradeoff Network (SATNet) for Lightweight RGB-D SOD from three fundamental perspectives: depth quality, modality fusion, and feature representation.
• Dual Mutual Learning Network with Global-local Awareness for RGB-D Salient Object Detection
  3 Jan 2025 1 repository listed
  RGB-D salient object detection (SOD), aiming to highlight prominent regions of a given scene by jointly modeling RGB and depth information, is one of the challenging pixel-level prediction tasks.
• MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object Detection
  19 Oct 2024 1 repository listed
  A primary challenge of this issue is how to fuse the complementary information from RGB and depth effectively.
• CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection
  9 Jul 2024 1 repository listed Syntology ran 8 of 11 samples · 3 unverified
  However, in dual-modal salient object detection (SOD) model, the robustness against noisy inputs and modality missing is crucial but rarely studied.
• DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
  18 Sep 2023 1 repository listed
  We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks.
• Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection
  6 Jun 2023 1 repository listed
  In particular, following the principle of disentangled representation learning, we introduce a mutual information upper bound with a mutual information minimization regularizer to encourage the disentangled…
• Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object Detection
  8 Aug 2022 1 repository listed
  Inspired by the fact that depth quality is a key factor influencing the accuracy, we propose an efficient depth quality-inspired feature manipulation (DQFM) process, which can dynamically filter depth features according…
• SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection
  16 Jul 2022 1 repository listed Syntology ran 2 of 3 samples · 1 unverified
  However, despite advances in deep learning-based methods, RGB-D SOD is still challenging due to the large domain gap between an RGB image and the depth map and low-quality depth maps.
• TANet: Transformer-based Asymmetric Network for RGB-D Salient Object Detection
  4 Jul 2022 1 repository listed
  We employ the powerful feature extraction capability of Transformer (PVTv2) to extract global semantic information from RGB data and design a lightweight CNN backbone (LWDepthNet) to extract spatial structure…
• Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection
  15 May 2022 1 repository listed Syntology ran 6 of 9 samples · 3 unverified
  The laborious and time-consuming manual annotation has become a real bottleneck in various practical scenarios.
• An Energy-Based Prior for Generative Saliency
  19 Apr 2022 1 repository listed
  We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution.
• Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction
  9 Mar 2022 1 repository listed Syntology ran 10 of 11 samples · 1 unverified
  In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD).
• Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images
  1 Jan 2022 1 repository listed
  The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data.
• CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
  4 Dec 2021 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  Most of the existing bi-modal (RGB-D and RGB-T) salient object detection methods utilize the convolution operation and construct complex interweave fusion structures to achieve cross-modal information integration.
• MutualFormer: Multi-Modality Representation Learning via Cross-Diffusion Attention
  2 Dec 2021 1 repository listed
  In this work, we re-think Transformer and extend it to MutualFormer for multi-modality data representation.
• Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection
  1 Dec 2021 1 repository listed
  As a by-product, a CapS dataset is constructed by augmenting existing benchmark training set with additional image tags and captions.
• TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network
  9 Aug 2021 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  In view of the more contribution of high-level features for the performance, we propose a triplet transformer embedding module to enhance them by learning long-range dependencies across layers.
• Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection
  4 Aug 2021 1 repository listed
  For the cross-modality interaction in feature encoder, existing methods either indiscriminately treat RGB and depth modalities, or only habitually utilize depth cues as auxiliary information of the RGB branch.

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-25.