Papers › URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth...

URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation

16 Feb 2023arXiv:2302.08149archive 2025-07-28

Shuwei Shao, Zhongcai Pei, Weihai Chen, Ran Li, Zhong Liu, Zhengguo Li

This work aims to estimate a high-quality depth map from a single RGB image. Due to the lack of depth clues, making full use of the long-range correlation and the local information is critical for accurate depth estimation. Towards this end, we introduce an uncertainty rectified cross-distillation between Transformer and convolutional neural network (CNN) to learn a unified depth estimator. Specifically, we use the depth estimates from the Transformer branch and the CNN branch as pseudo labels to teach each other. Meanwhile, we model the pixel-wise depth uncertainty to rectify the loss weights of noisy pseudo labels. To avoid the large capacity gap induced by the strong Transformer branch deteriorating the cross-distillation, we transfer the feature maps from Transformer to CNN and design coupling units to assist the weak CNN branch to leverage the transferred features. Furthermore, we propose a surprisingly simple yet highly effective data augmentation technique CutFlip, which enforces the model to exploit more valuable clues apart from the vertical image position for depth inference. Extensive experiments demonstrate that our model, termed~\textbf{URCDC-Depth}, exceeds previous state-of-the-art methods on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets, even with no additional computational burden at inference time. The source code is publicly available at \url{https://github.com/ShuweiShao/URCDC-Depth}.

PaperPDFCodeCode 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="2302.08149")

Code

Syntology Ran 5 of 11 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shuweishao/urcdc-depth officialmentioned in papermentioned 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

11 samples harvested; 5 ran; 1 honoured the contract we drafted; 6 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 · honoured contract
1ran · our draft was wrong
1ran · fixture could not drive it
2ran
6unverified

Licence: 0 of the 11 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 shuweishao/urcdc-depth. “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.

window_partition shuweishao/urcdc-depth/urcdc/networks/newcrf_layers.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report
get_num_lines shuweishao/urcdc-depth/urcdc/utils.py official repository ran · honoured contract MIT (permissive) · 050c56fb7282eb88 · report
normalize_result shuweishao/urcdc-depth/urcdc/utils.py official repository ran MIT (permissive) · 8a05ea4d5e917bf4 · report
upsample shuweishao/urcdc-depth/urcdc/networks/NewCRFDepth.py official repository ran MIT (permissive) · 35e6bae6a3fe0669 · report
window_reverse shuweishao/urcdc-depth/urcdc/networks/newcrf_layers.py official repository ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report
colorize shuweishao/urcdc-depth/urcdc/utils.py official repository unverified MIT (permissive) · 9999af2cf9c1b6bb · report
is_module_wrapper shuweishao/urcdc-depth/urcdc/networks/newcrf_utils.py official repository unverified MIT (permissive) · 9b9dd29ad0d626a0 · report
load_url_dist shuweishao/urcdc-depth/urcdc/networks/newcrf_utils.py official repository unverified MIT (permissive) · 92dad73ee855852f · report
preprocessing_transforms shuweishao/urcdc-depth/urcdc/dataloaders/dataloader.py official repository unverified MIT (permissive) · 4f7c1c530e5b46be · report
preprocessing_transforms shuweishao/urcdc-depth/urcdc/dataloaders/dataloader_kittipred.py official repository unverified MIT (permissive) · ea623328271af85a · report
resize shuweishao/urcdc-depth/urcdc/networks/newcrf_utils.py official repository unverified MIT (permissive) · 9012d3fdd4cbaea1 · report

Tasks

Data AugmentationDepth EstimationMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split URCDC-Depth Delta < 1.25 0.977 #20 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split URCDC-Depth Delta < 1.25^2 0.997 #20 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split URCDC-Depth Delta < 1.25^3 0.999 #20 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split URCDC-Depth RMSE 2.032 #20 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split URCDC-Depth RMSE log 0.076 #20 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split URCDC-Depth Sq Rel 0.142 #20 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split URCDC-Depth absolute relative error 0.050 #20 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 URCDC-Depth Delta < 1.25 0.933 #36 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 URCDC-Depth Delta < 1.25^2 0.992 #36 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 URCDC-Depth Delta < 1.25^3 0.998 #36 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 URCDC-Depth RMSE 0.316 #36 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 URCDC-Depth absolute relative error 0.088 #36 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 URCDC-Depth log 10 0.038 #36 of 85 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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