Papers › High Quality Monocular Depth Estimation via Transfer Learning

High Quality Monocular Depth Estimation via Transfer Learning

31 Dec 2018arXiv:1812.11941archive 2025-07-28

Ibraheem Alhashim, Peter Wonka

Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction. Existing solutions for depth estimation often produce blurry approximations of low resolution. This paper presents a convolutional neural network for computing a high-resolution depth map given a single RGB image with the help of transfer learning. Following a standard encoder-decoder architecture, we leverage features extracted using high performing pre-trained networks when initializing our encoder along with augmentation and training strategies that lead to more accurate results. We show how, even for a very simple decoder, our method is able to achieve detailed high-resolution depth maps. Our network, with fewer parameters and training iterations, outperforms state-of-the-art on two datasets and also produces qualitatively better results that capture object boundaries more faithfully. Code and corresponding pre-trained weights are made publicly available.

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="1812.11941")

Code

Syntology Ran 5 of 23 code samples harvested from 4 repositories linked to this paper; 18 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 23 samples from 4 repositories, 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.

45 repositories listed; official and paper-mentioned ones first.

ialhashim/DenseDepth officialmentioned in papermentioned on GitHubtfGPL-3.0 report
AmirsSaad/UWPhysDepth mentioned on GitHubtfGPL-3.0 report
BalajiAJ/DenseDepth mentioned on GitHubtfGPL-3.0 report
Deeksha-Pandit/EVA4-S10 mentioned on GitHubtf report
JahnaviRamagiri/DenseDepth_1 mentioned on GitHubtfGPL-3.0 report
NSR9/DenseDepth mentioned on GitHubtfGPL-3.0 report
Noopuragr/DepthModel mentioned on GitHubtfGPL-3.0 report
Ruby1302/DenseDepth mentioned on GitHubtfGPL-3.0 report
Ruby1302/DenseDepth_1 mentioned on GitHubtfGPL-3.0 report
Sushmitha-Katti/DepthModel mentioned on GitHubtfGPL-3.0 report
aimbsg/EVA4_S15 mentioned on GitHubpytorch report
alinstein/Depth_estimation mentioned on GitHubpytorchMIT report
avinashpaul2012/neophyte mentioned on GitHubtfGPL-3.0 report
daniallin/DenseDepth-Pytorch mentioned on GitHubpytorch report
deepjyotisaha85/DenseDepth mentioned on GitHubtfGPL-3.0 report
dorsadadjoo/Distance_Estimation mentioned on GitHubtfGPL-3.0 report
dsshim0125/grmc mentioned on GitHubpytorchMIT report
gudaykiran/DepthModel mentioned on GitHubtfGPL-3.0 report
jojo13572001/DenseDepth mentioned on GitHubtfGPL-3.0 report
l0stpenguin/DenseDepthResNet mentioned on GitHubtf report
lemon-liley/isabella mentioned on GitHubpytorchMIT report
mshilpaa/DenseDepth mentioned on GitHubtfGPL-3.0 report
raajeshlr/DenseDepth mentioned on GitHubtfGPL-3.0 report
rain58/boundary-aware-image-inpainting mentioned on GitHubpytorchMIT report
ranjanguddu/DenseImageModel mentioned on GitHubtfGPL-3.0 report
ranjanguddu/DenseModel mentioned on GitHubtfGPL-3.0 report
roshantac/DenseDepth mentioned on GitHubtfGPL-3.0 report
rramjee/DenseDepth mentioned on GitHubtf report
rsha0812/DenseDepth mentioned on GitHubtfGPL-3.0 report
satyajitghana/DenseDepth mentioned on GitHubtfGPL-3.0 report
seenu-g/DepthModel mentioned on GitHubtfGPL-3.0 report
seepala98/DenseDepth mentioned on GitHubtfGPL-3.0 report
siddinc/monocular_depth_estimation mentioned on GitHubtfGPL-3.0 report
srilakshmiv14/DepthModel mentioned on GitHubtfGPL-3.0 report
thiagorjes/depth_estimation mentioned on GitHubtf 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

23 samples harvested; 5 ran; 2 honoured the contract we drafted; 18 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.

2ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it
18unverified

Licence: 3 of the 23 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 4 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.

DepthNorm rramjee/DenseDepth/Tensorflow/evaluate.py community (archive-listed) ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · 1852f926ecf3ccc4 · report
display_single_image KarthikGangadhar/depth-estimation/video_display.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · d84535097384ce79 · report
gaussian dsshim0125/grmc/loss.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report
lr_pad lemon-liley/isabella/HorizonNet/model.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · fb884f33b5fda8ea · report
predict rramjee/DenseDepth/Tensorflow/evaluate.py community (archive-listed) ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 6ce438ff124a45a8 · report
DepthNorm dsshim0125/grmc/utils.py community (archive-listed) unverified MIT (permissive) · d57ca4e488622dcb · report
augment lemon-liley/isabella/HorizonNet/inference.py community (archive-listed) unverified MIT (permissive) · 6c798decc8af5b44 · report
augment_undo lemon-liley/isabella/HorizonNet/inference.py community (archive-listed) unverified MIT (permissive) · d7030b9fc8555db4 · report
choose_decoder dsshim0125/grmc/model/fcrn.py community (archive-listed) unverified MIT (permissive) · b3d7054d301b12b6 · report
create_window dsshim0125/grmc/loss.py community (archive-listed) unverified MIT (permissive) · 443341084ce76798 · report
depth_loss_function lemon-liley/isabella/loss.py community (archive-listed) unverified MIT (permissive) · dddbd5a319a669ff · report
extract_zip dsshim0125/grmc/evaluate_pytorch.py community (archive-listed) unverified MIT (permissive) · 58071b7eba94ccbd · report
find_N_peaks lemon-liley/isabella/HorizonNet/inference.py community (archive-listed) unverified MIT (permissive) · 2c99a936790c4965 · report
getNoTransform dsshim0125/grmc/data.py community (archive-listed) unverified MIT (permissive) · 8d2d575309864698 · report
loadZipToMem dsshim0125/grmc/data.py community (archive-listed) unverified MIT (permissive) · 744ce2b9aed9a499 · report
loadZipToMem_test dsshim0125/grmc/data.py community (archive-listed) unverified MIT (permissive) · 95089e2ebb03ecf5 · report
make_image lemon-liley/isabella/callbacks.py community (archive-listed) unverified MIT (permissive) · a5c4a0adfc21338d · report
predict dsshim0125/grmc/utils.py community (archive-listed) unverified MIT (permissive) · 9637ab8ac25f366c · report
scale_up rramjee/DenseDepth/Tensorflow/evaluate.py community (archive-listed) unverified GPL-3.0 (copyleft) · pointer only · 229418e47c5aa9bc · report
sort_xy_filter_unique lemon-liley/isabella/HorizonNet/dataset.py community (archive-listed) unverified MIT (permissive) · 87dffac4821848bf · report
ssim dsshim0125/grmc/loss.py community (archive-listed) unverified MIT (permissive) · 983373e062ffdb0f · report
tri2halfspace lemon-liley/isabella/HorizonNet/eval_cuboid.py community (archive-listed) unverified MIT (permissive) · 7525fc8039cc75b5 · report
xyzlst2halfspaces lemon-liley/isabella/HorizonNet/eval_cuboid.py community (archive-listed) unverified MIT (permissive) · 373920e32dc5fdb1 · report

Tasks

Action ClassificationDecoderDepth EstimationMonocular Depth EstimationTransfer LearningVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split DenseDepth absolute relative error 0.093 #51 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 DenseDepth RMSE 0.465 #63 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.

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