Browse State-of-the-Art › RGB-D Salient Object Detection
RGB-D Salient Object Detection
61 papers with code · 8 benchmarks · 5 datasets archive 2025-07-28
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 )
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
Papers archive 2025-07-28
archive papers tagged: 88 · with a code link: 61 · where Syntology ran a sample: 14 (11 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (14 of 88 tagged: 11 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 88 of 88, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
1 Aug 2020 9 repositories listedFurther, considering that the light field can also provide depth maps, we review SOD models and popular benchmark datasets from this domain as well.
-
7 Sep 2020 4 repositories listedOur 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…
-
6 Oct 2022 3 repositories listedFocusing 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…
-
17 Aug 2023 2 repositories listedBy integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved.
-
25 Apr 2021 2 repositories listed Syntology 7 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples) · 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.
-
26 Aug 2020 2 repositories listedInspired 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…
-
23 Jul 2020 2 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)The explicitly extracted edge information goes together with saliency to give more emphasis to the salient regions and object boundaries.
-
9 Jul 2020 2 repositories listed Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)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.
-
6 Jul 2020 2 repositories listed Syntology official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 2 pointer-only (licence)In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS).
-
15 Jul 2019 2 repositories listedThe use of RGB-D information for salient object detection has been extensively explored in recent years.
-
1 Jun 2019 2 repositories listedThe large availability of depth sensors provides valuable complementary information for salient object detection (SOD) in RGBD images.
-
23 Mar 2018 2 repositories listedOne is the lack of tremendous amount of annotated data to train a network.
-
7 May 2025 1 repository listedTo 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.
-
3 Jan 2025 1 repository listedRGB-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.
-
19 Oct 2024 1 repository listedA primary challenge of this issue is how to fuse the complementary information from RGB and depth effectively.
-
9 Jul 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples) · 4 pointer-only (licence)However, in dual-modal salient object detection (SOD) model, the robustness against noisy inputs and modality missing is crucial but rarely studied.
-
18 Sep 2023 1 repository listedWe present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks.
-
6 Jun 2023 1 repository listedIn 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…
-
8 Aug 2022 1 repository listedInspired 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…
-
16 Jul 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)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.
-
4 Jul 2022 1 repository listedWe 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…
-
15 May 2022 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 3 pointer-only (licence)The laborious and time-consuming manual annotation has become a real bottleneck in various practical scenarios.
-
19 Apr 2022 1 repository listedWe propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution.
-
9 Mar 2022 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 11 harvested samples)In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD).
-
1 Jan 2022 1 repository listedThe 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.
-
4 Dec 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)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.
-
2 Dec 2021 1 repository listedIn this work, we re-think Transformer and extend it to MutualFormer for multi-modality data representation.
-
1 Dec 2021 1 repository listedAs a by-product, a CapS dataset is constructed by augmenting existing benchmark training set with additional image tags and captions.
-
9 Aug 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 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.
-
4 Aug 2021 1 repository listedFor 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.
-
5 Jul 2021 1 repository listed
-
19 Jun 2021 1 repository listed
-
5 Apr 2021 1 repository listed
-
22 Mar 2021 1 repository listed
-
12 Feb 2021 1 repository listed
-
29 Jan 2021 1 repository listed
-
25 Jan 2021 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 13 harvested samples)
-
24 Dec 2020 1 repository listed
-
12 Oct 2020 1 repository listed
-
17 Aug 2020 1 repository listed
-
7 Aug 2020 1 repository listed
-
7 Aug 2020 1 repository listed
-
7 Aug 2020 1 repository listed
-
7 Aug 2020 1 repository listed
-
1 Aug 2020 1 repository listed
-
14 Jul 2020 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
14 Jul 2020 1 repository listed
-
13 Jul 2020 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 2 pointer-only (licence)
-
1 Jun 2020 1 repository listed
-
1 Jun 2020 1 repository listed
-
1 Jun 2020 1 repository listed
-
30 May 2020 1 repository listed
-
30 Apr 2020 1 repository listed
-
18 Apr 2020 1 repository listed
-
13 Apr 2020 1 repository listed
-
12 Apr 2020 1 repository listed
-
19 Mar 2020 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples)
-
21 Dec 2019 1 repository listed
-
1 Oct 2019 1 repository listed
-
5 Jan 2019 1 repository listed
-
1 Jun 2018 1 repository listed
-
A Saliency Enhanced Feature Fusion based multiscale RGB-D Salient Object Detection Network22 Jan 2024 0 repositories listed
-
Decomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completion5 Sep 2023 0 repositories listed
-
HODINet: High-Order Discrepant Interaction Network for RGB-D Salient Object Detection3 Jul 2023 0 repositories listed
-
RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection22 Jun 2023 0 repositories listed
-
Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection16 Feb 2023 0 repositories listed
-
HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness18 Jan 2023 0 repositories listed
-
SiaTrans: Siamese Transformer Network for RGB-D Salient Object Detection with Depth Image Classification9 Jul 2022 0 repositories listed
-
Dynamic Message Propagation Network for RGB-D Salient Object Detection20 Jun 2022 0 repositories listed
-
Dual Swin-Transformer based Mutual Interactive Network for RGB-D Salient Object Detection7 Jun 2022 0 repositories listed
-
GroupTransNet: Group Transformer Network for RGB-D Salient Object Detection21 Mar 2022 0 repositories listed
-
Multi-Scale Iterative Refinement Network for RGB-D Salient Object Detection24 Jan 2022 0 repositories listed
-
27 Dec 2021 0 repositories listed
-
M2RNet: Multi-modal and Multi-scale Refined Network for RGB-D Salient Object Detection16 Sep 2021 0 repositories listed
-
ACFNet: Adaptively-Cooperative Fusion Network for RGB-D Salient Object Detection10 Sep 2021 0 repositories listed
-
8 Sep 2021 0 repositories listed
-
Modal-Adaptive Gated Recoding Network for RGB-D Salient Object Detection13 Aug 2021 0 repositories listed
-
Dynamic Knowledge Distillation With Noise Elimination for RGB-D Salient Object Detection17 Jun 2021 0 repositories listed
-
Progressive Multi-scale Fusion Network for RGB-D Salient Object Detection7 Jun 2021 0 repositories listed
-
Middle-level Fusion for Lightweight RGB-D Salient Object Detection23 Apr 2021 0 repositories listed
-
A Unified Structure for Efficient RGB and RGB-D Salient Object Detection1 Dec 2020 0 repositories listed
-
Multi-level Cross-modal Interaction Network for RGB-D Salient Object Detection10 Jul 2020 0 repositories listed
-
CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse20 Sep 2019 0 repositories listed
-
2D Car Detection in Radar Data with PointNets17 Apr 2019 0 repositories listed
-
Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features10 May 2017 0 repositories listed
-
RGB-D Salient Object Detection Based on Discriminative Cross-modal Transfer Learning1 Mar 2017 0 repositories listed
-
12 Jul 2016 0 repositories listed
-
1 Jun 2016 0 repositories listed
Syntology lines on 14 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections