Papers › Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D...

Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing

18 Jul 2020ECCV 2020 8arXiv:2007.09365archive 2025-07-28

Yajie Xing, Jingbo Wang, Gang Zeng

Depth data provide geometric information that can bring progress in RGB-D scene parsing tasks. Several recent works propose RGB-D convolution operators that construct receptive fields along the depth-axis to handle 3D neighborhood relations between pixels. However, these methods pre-define depth receptive fields by hyperparameters, making them rely on parameter selection. In this paper, we propose a novel operator called malleable 2.5D convolution to learn the receptive field along the depth-axis. A malleable 2.5D convolution has one or more 2D convolution kernels. Our method assigns each pixel to one of the kernels or none of them according to their relative depth differences, and the assigning process is formulated as a differentiable form so that it can be learnt by gradient descent. The proposed operator runs on standard 2D feature maps and can be seamlessly incorporated into pre-trained CNNs. We conduct extensive experiments on two challenging RGB-D semantic segmentation dataset NYUDv2 and Cityscapes to validate the effectiveness and the generalization ability of our method.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2007.09365")

Code

Syntology Ran 4 of 14 code samples harvested from 2 repositories linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 5 samples from 1 repository, 3 ran; community (archive-listed): 9 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

charlesCXK/RGBD_Semantic_Segmentation_PyTorch officialmentioned on GitHubpytorchMIT report
David-zaiwang/114_rgbd_seg mentioned on GitHubpytorchMIT 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

14 samples harvested; 4 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
10unverified

Licence: 0 of the 14 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

conv1x1 charlesCXK/RGBD_Semantic_Segmentation_PyTorch/model/SA-Gate.nyu.432/net_util.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 charlesCXK/RGBD_Semantic_Segmentation_PyTorch/furnace/base_model/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
normalize charlesCXK/RGBD_Semantic_Segmentation_PyTorch/model/SA-Gate.nyu.432/dataloader.py official repository ran · violated contract fingerprinted MIT (permissive) · 17cb5b0dfa01b491 · report
random_mirror charlesCXK/RGBD_Semantic_Segmentation_PyTorch/model/SA-Gate.nyu.432/dataloader.py official repository unverified MIT (permissive) · 6e022fd18a9397fa · report
random_scale charlesCXK/RGBD_Semantic_Segmentation_PyTorch/model/SA-Gate.nyu.432/dataloader.py official repository unverified MIT (permissive) · eda7f5af7267de5d · report
hist_info David-zaiwang/114_rgbd_seg/furnace/seg_opr/metric.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 9e85fa995eda358a · report
batchnormtrain David-zaiwang/114_rgbd_seg/furnace/seg_opr/sync_bn/functions.py community (archive-listed) unverified MIT (permissive) · 5c906904c2492dc7 · report
compute_score David-zaiwang/114_rgbd_seg/furnace/seg_opr/metric.py community (archive-listed) unverified MIT (permissive) · 3e98ad928a86de29 · report
get_a_var David-zaiwang/114_rgbd_seg/furnace/seg_opr/parallel/parallel_apply.py community (archive-listed) unverified MIT (permissive) · 74bcab5cc9c8e91b · report
meanIoU David-zaiwang/114_rgbd_seg/furnace/seg_opr/metric.py community (archive-listed) unverified MIT (permissive) · be62e3869efd8038 · report
parallel_apply David-zaiwang/114_rgbd_seg/furnace/seg_opr/parallel/parallel_apply.py community (archive-listed) unverified MIT (permissive) · c490830f0e503906 · report
parallel_apply David-zaiwang/114_rgbd_seg/furnace/seg_opr/sync_bn/parallel_apply.py community (archive-listed) unverified MIT (permissive) · 58954eadae7321d1 · report
patch_replication_callback David-zaiwang/114_rgbd_seg/furnace/seg_opr/sync_bn/parallel.py community (archive-listed) unverified MIT (permissive) · 27e207fe8a74c3e7 · report
sum_square David-zaiwang/114_rgbd_seg/furnace/seg_opr/sync_bn/functions.py community (archive-listed) unverified MIT (permissive) · 8a79f49da87d44bf · report

Tasks

Scene ParsingSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation NYU Depth v2 Malleable 2.5D (ResNet-101) Mean IoU 50.9% #58 of 121 Archive leaderboard report
Semantic Segmentation NYU Depth v2 Malleable 2.5D (ResNet-50) Mean IoU 49.7% #67 of 121 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.

Methods

Convolution

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