Papers › NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation

NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation

3 Mar 2022CVPR 2022 3arXiv:2203.01502archive 2025-07-28

Weihao Yuan, Xiaodong Gu, Zuozhuo Dai, Siyu Zhu, Ping Tan

Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful networks to directly regress the depth map, we take the path of CRFs optimization. Due to the expensive computation, CRFs are usually performed between neighborhoods rather than the whole graph. To leverage the potential of fully-connected CRFs, we split the input into windows and perform the FC-CRFs optimization within each window, which reduces the computation complexity and makes FC-CRFs feasible. To better capture the relationships between nodes in the graph, we exploit the multi-head attention mechanism to compute a multi-head potential function, which is fed to the networks to output an optimized depth map. Then we build a bottom-up-top-down structure, where this neural window FC-CRFs module serves as the decoder, and a vision transformer serves as the encoder. The experiments demonstrate that our method significantly improves the performance across all metrics on both the KITTI and NYUv2 datasets, compared to previous methods. Furthermore, the proposed method can be directly applied to panorama images and outperforms all previous panorama methods on the MatterPort3D dataset. Project page: https://weihaosky.github.io/newcrfs.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2203.01502")

Code

Syntology Ran 6 of 10 code samples harvested from 1 repository linked to this paper; 4 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; 3 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

aliyun/NeWCRFs officialmentioned 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

10 samples harvested; 6 ran; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; 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
3ran
4unverified

Licence: 10 of the 10 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 aliyun/NeWCRFs. “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 aliyun/NeWCRFs/newcrfs/networks/newcrf_layers.py official repository ran · fixture could not drive it fingerprinted MIT recorded; this copy not marked cleared · pointer only · 144d10b49baeb8a6 · report
get_num_lines aliyun/NeWCRFs/newcrfs/utils.py official repository ran · honoured contract MIT recorded; this copy not marked cleared · pointer only · 050c56fb7282eb88 · report
normalize_result aliyun/NeWCRFs/newcrfs/utils.py official repository ran MIT recorded; this copy not marked cleared · pointer only · 8a05ea4d5e917bf4 · report
preprocessing_transforms aliyun/NeWCRFs/newcrfs/dataloaders/dataloader.py official repository ran MIT recorded; this copy not marked cleared · pointer only · ea623328271af85a · report
upsample aliyun/NeWCRFs/newcrfs/networks/NewCRFDepth.py official repository ran MIT recorded; this copy not marked cleared · pointer only · 35e6bae6a3fe0669 · report
window_reverse aliyun/NeWCRFs/newcrfs/networks/newcrf_layers.py official repository ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 61bf152e6a42a184 · report
colorize aliyun/NeWCRFs/newcrfs/utils.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 9999af2cf9c1b6bb · report
is_module_wrapper aliyun/NeWCRFs/newcrfs/networks/newcrf_utils.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 9b9dd29ad0d626a0 · report
load_url_dist aliyun/NeWCRFs/newcrfs/networks/newcrf_utils.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 92dad73ee855852f · report
resize aliyun/NeWCRFs/newcrfs/networks/newcrf_utils.py official repository unverified MIT recorded; this copy not marked cleared · pointer only · 9012d3fdd4cbaea1 · report

Tasks

DecoderDepth EstimationDepth PredictionMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split NeWCRFs Delta < 1.25 0.974 #27 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split NeWCRFs Delta < 1.25^2 0.997 #27 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split NeWCRFs Delta < 1.25^3 0.999 #27 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split NeWCRFs RMSE 2.129 #27 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split NeWCRFs RMSE log 0.079 #27 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split NeWCRFs Sq Rel 0.155 #27 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split NeWCRFs absolute relative error 0.052 #27 of 79 Archive leaderboard report
Monocular Depth Estimation Matterport3D NeWCRFs Delta < 1.25 0.9376 #1 of 1 Archive leaderboard report
Monocular Depth Estimation Matterport3D NeWCRFs Delta < 1.25^2 0.9812 #1 of 1 Archive leaderboard report
Monocular Depth Estimation Matterport3D NeWCRFs Delta < 1.25^3 0.9933 #1 of 1 Archive leaderboard report
Monocular Depth Estimation Matterport3D NeWCRFs RMSE 0.4279 #1 of 1 Archive leaderboard report
Monocular Depth Estimation Matterport3D NeWCRFs absolute error 0.197 #1 of 1 Archive leaderboard report
Monocular Depth Estimation Matterport3D NeWCRFs absolute relative error 0.0793 #1 of 1 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 NeWCRFs Delta < 1.25 0.922 #43 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 NeWCRFs Delta < 1.25^2 0.992 #43 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 NeWCRFs Delta < 1.25^3 0.998 #43 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 NeWCRFs RMSE 0.334 #43 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 NeWCRFs absolute relative error 0.095 #43 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 NeWCRFs log 10 0.041 #43 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

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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