Papers › RGB-D Salient Object Detection via 3D Convolutional Neural Networks

RGB-D Salient Object Detection via 3D Convolutional Neural Networks

25 Jan 2021arXiv:2101.10241archive 2025-07-28

Qian Chen, Ze Liu, Yi Zhang, Keren Fu, Qijun Zhao, Hongwei Du

RGB-D salient object detection (SOD) recently has attracted increasing research interest and many deep learning methods based on encoder-decoder architectures have emerged. However, most existing RGB-D SOD models conduct feature fusion either in the single encoder or the decoder stage, which hardly guarantees sufficient cross-modal fusion ability. In this paper, we make the first attempt in addressing RGB-D SOD through 3D convolutional neural networks. The proposed model, named RD3D, aims at pre-fusion in the encoder stage and in-depth fusion in the decoder stage to effectively promote the full integration of RGB and depth streams. Specifically, RD3D first conducts pre-fusion across RGB and depth modalities through an inflated 3D encoder, and later provides in-depth feature fusion by designing a 3D decoder equipped with rich back-projection paths (RBPP) for leveraging the extensive aggregation ability of 3D convolutions. With such a progressive fusion strategy involving both the encoder and decoder, effective and thorough interaction between the two modalities can be exploited and boost the detection accuracy. Extensive experiments on six widely used benchmark datasets demonstrate that RD3D performs favorably against 14 state-of-the-art RGB-D SOD approaches in terms of four key evaluation metrics. Our code will be made publicly available: https://github.com/PPOLYpubki/RD3D.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 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. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 9 ran (5 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

PPOLYpubki/RD3D officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 9 ran (4 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
5ran
4unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from PPOLYpubki/RD3D. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

PPOLYpubki/RD3D official repository 13 samples, 9 ran (4 instrument-failed) · 4 unverified
BasicConv3d model/rd3d.py ran MIT (permissive) · a11ba11d88e6025c · report fixture: returned BasicConv3d · level recorded 2026-09-22
Bottleneck3d model/rd3d.py ran MIT (permissive) · 142151bb8fc9a0dd · report fixture: returned Bottleneck3d · level recorded 2026-09-22
CMA model/rd3d.py ran fingerprinted MIT (permissive) · 12a040f3dfce9876 · report fixture: returned CMA · level recorded 2026-09-22
I3DResNet model/rd3d.py ran fingerprinted MIT (permissive) · 2da47d0afe813abb · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
Reduction3D model/rd3d.py ran MIT (permissive) · 58c8a7058368f8fc · report fixture: returned Reduction3D · level recorded 2026-09-22
inflate_batch_norm model/rd3d.py ran · our draft was wrong MIT (permissive) · 457cc8c6dc365fbc · report fixture: signature batch2d:callable/0/? · returned BatchNorm2d · level recorded 2026-09-22
inflate_conv model/rd3d.py ran · our draft was wrong MIT (permissive) · 462a009bfe9dee63 · report fixture: signature conv2d:callable/0/?, time_dim:int/0/int, time_padding:int/0/int, time_stride:int/0/int, time_dilation:int/0/int, center:bool/0/bool · returned Conv3d · level recorded 2026-09-22
inflate_downsample model/rd3d.py ran · our draft was wrong MIT (permissive) · f2685bfb0f379f62 · report fixture: signature downsample2d:callable/0/?, time_stride:int/0/int · returned Sequential · level recorded 2026-09-22
inflate_pool model/rd3d.py ran · our draft was wrong MIT (permissive) · 5746a7a29dd3f77d · report fixture: signature pool2d:callable/0/?, time_dim:int/0/int, time_padding:int/0/int, time_stride:int/0/int, time_dilation:int/0/int · returned MaxPool3d · level recorded 2026-09-22
RD3D model/rd3d.py unverified MIT (permissive) · 604a8608bbcb5fc6 · report
ThreeDDecoder model/rd3d.py unverified MIT (permissive) · 7b64667c719c3c2e · report
Unet3D model/rd3d.py unverified MIT (permissive) · bca52ce74c61b15f · report
inflate_reslayer model/rd3d.py unverified MIT (permissive) · a45223f97a51625c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for RD3D (graph method: RD3D). 14 bricks; individually on a fixture: 10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. RD3D entry · level 0 · unverified · 604a8608bbcb5fc6
  2. I3DResNet model · level 1 · ran · 2da47d0afe813abb
  3. Unet3D model · level 0 · unverified · bca52ce74c61b15f
  4. inflate_batch_norm helper · level 1 · ran · our draft was wrong · 457cc8c6dc365fbc
  5. inflate_conv helper · level 1 · ran · our draft was wrong · 462a009bfe9dee63
  6. inflate_pool helper · level 1 · ran · our draft was wrong · 5746a7a29dd3f77d
  7. inflate_reslayer helper · level 0 · unverified · a45223f97a51625c
  8. Reduction3D model · level 1 · ran · 58c8a7058368f8fc
  9. ThreeDDecoder helper · level 0 · unverified · 7b64667c719c3c2e
  10. Bottleneck3d helper · level 1 · ran · 142151bb8fc9a0dd
  11. BasicConv3d helper · level 1 · ran · a11ba11d88e6025c
  12. BasicConv2d helper · level 1 · ran · 9d65fd2b9de9e302
  13. CMA helper · level 1 · ran · 12a040f3dfce9876
  14. inflate_downsample helper · level 1 · ran · our draft was wrong · f2685bfb0f379f62

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2101.10241") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderObject DetectionRGB-D Salient Object DetectionSalient Object DetectionThermal Image Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Thermal Image Segmentation RGB-T-Glass-Segmentation RD3D MAE 0.045 #8 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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