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 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

The archive's official repository (ialhashim/DenseDepth) was not harvested; the 23 samples below come from 4 community repositories.

Syntology 23 code samples harvested from 4 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 23 samples from 4 repositories, 19 ran (16 with no instrument failure; 3 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 19 samples that ran has no recorded date.

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

ialhashim/DenseDepth officialmentioned in papermentioned on GitHubtfGPL-3.0Syntology: not harvested report
AmirsSaad/UWPhysDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
BalajiAJ/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
Deeksha-Pandit/EVA4-S10 mentioned on GitHubtfSyntology: not harvested report
Intoxillectual/Monocular-Depth-Estimation-using-DenseNet169 mentioned on GitHubtfSyntology: not harvested report
JahnaviRamagiri/DenseDepth_1 mentioned on GitHubtfGPL-3.0Syntology: not harvested report
KarthikGangadhar/depth-estimation mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
MahyarFardin/Monocular_depth_estimation_via_transfer_learning mentioned on GitHubpytorchSyntology: not harvested report
NSR9/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
NiallEHunt/MonocularDepth-Using-LightFields mentioned on GitHubpytorchSyntology: not harvested report
Noopuragr/DepthModel mentioned on GitHubtfGPL-3.0Syntology: not harvested report
Ruby1302/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
Ruby1302/DenseDepth_1 mentioned on GitHubtfGPL-3.0Syntology: not harvested report
Sushmitha-Katti/DepthModel mentioned on GitHubtfGPL-3.0Syntology: not harvested report
WeLoveKiraboshi/In-PlaneRotation-AwareDepthEstimation mentioned on GitHubNOASSERTIONSyntology: not harvested report
WeLoveKiraboshi/In-PlaneRotationAwareDepthEstimation mentioned on GitHubNOASSERTIONSyntology: not harvested report
aimbsg/EVA4_S15 mentioned on GitHubpytorchSyntology: not harvested report
alinstein/Depth_estimation mentioned on GitHubpytorchMITSyntology: not harvested report
avinashpaul2012/neophyte mentioned on GitHubtfGPL-3.0Syntology: not harvested report
brandon-wu76/monocular-depth-estimation mentioned on GitHubSyntology: not harvested report
daniallin/DenseDepth-Pytorch mentioned on GitHubpytorchSyntology: not harvested report
deepjyotisaha85/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
dorsadadjoo/Distance_Estimation mentioned on GitHubtfGPL-3.0Syntology: not harvested report
dsshim0125/grmc mentioned on GitHubpytorchMITSyntology: 10 samples, 9 ran (0 instrument-failed) · 1 unverified report
gudaykiran/DepthModel mentioned on GitHubtfGPL-3.0Syntology: not harvested report
jojo13572001/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
l0stpenguin/DenseDepthResNet mentioned on GitHubtfSyntology: not harvested report
lemon-liley/isabella mentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (1 instrument-failed) · 2 unverified report
mshilpaa/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
raajeshlr/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
rain58/boundary-aware-image-inpainting mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DIODE: A Dense Indoor and Outdoor DEpth Dataset (arXiv:1908.00463; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ranjanguddu/DenseImageModel mentioned on GitHubtfGPL-3.0Syntology: not harvested report
ranjanguddu/DenseModel mentioned on GitHubtfGPL-3.0Syntology: not harvested report
roshantac/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
rramjee/DenseDepth mentioned on GitHubtfSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
rsha0812/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
satyajitghana/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
seenu-g/DepthModel mentioned on GitHubtfGPL-3.0Syntology: not harvested report
seepala98/DenseDepth mentioned on GitHubtfGPL-3.0Syntology: not harvested report
siddinc/monocular_depth_estimation mentioned on GitHubtfGPL-3.0Syntology: not harvested report
srilakshmiv14/DepthModel mentioned on GitHubtfGPL-3.0Syntology: not harvested report
thiagorjes/depth_estimation mentioned on GitHubtfSyntology: not harvested report
stunback/DenseDepth-paddle paddleNOASSERTIONSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

23 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 3 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
13ran
4unverified

Licence: 4 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

KarthikGangadhar/depth-estimation community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
display_single_image video_display.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · d84535097384ce79 · report fixture: signature output:ndarray/3/float, inputs:ndarray/3/float, is_colormap:bool/0/bool · returned ndarray · level recorded 2026-09-22
dsshim0125/grmc community (archive-listed) 10 samples, 9 ran (0 instrument-failed) · 1 unverified
DepthNorm utils.py ran fingerprinted MIT (permissive) · d57ca4e488622dcb · report fixture: signature depth:Tensor/2/float, maxDepth:float/0/float · returned Tensor · level recorded 2026-09-26
create_window in 82 papers loss.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 443341084ce76798 · report fixture: signature window_size:int/0/int, channel:int/0/int · returned Tensor · level recorded 2026-09-25
extract_zip evaluate_pytorch.py ran MIT (permissive) · 58071b7eba94ccbd · report fixture: signature input_zip:BytesIO/0/? · returned dict · level recorded 2026-09-26
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
loss.py ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report fixture: signature window_size:int/0/int, sigma:float/0/float · returned Tensor · level recorded, date not recorded
getNoTransform data.py ran MIT (permissive) · 8d2d575309864698 · report fixture: signature is_test:bool/0/bool · returned Compose · level recorded 2026-09-26
loadZipToMem data.py ran MIT (permissive) · 744ce2b9aed9a499 · report fixture: signature zip_file:str/0/str · returned tuple · level recorded 2026-09-26
loadZipToMem_test data.py ran MIT (permissive) · 95089e2ebb03ecf5 · report fixture: signature zip_file:str/0/str · returned tuple · level recorded 2026-09-26
predict in 126 papers utils.py ran MIT (permissive) · 9637ab8ac25f366c · report fixture: signature model:callable/0/?, images:ndarray/2/float, minDepth:int/0/int, maxDepth:int/0/int, batch_size:int/0/int · returned ndarray · level recorded 2026-09-26
ssim in 112 papers loss.py ran MIT (permissive) · 983373e062ffdb0f · report fixture: signature img1:Tensor/4/float, img2:Tensor/4/float, val_range:float/0/float, window_size:int/0/int, window:NoneType/0/?, size_average:bool/0/bool, full:bool/0/bool · returned Tensor · level recorded 2026-09-26
choose_decoder model/fcrn.py unverified MIT (permissive) · b3d7054d301b12b6 · report
lemon-liley/isabella community (archive-listed) 9 samples, 7 ran (1 instrument-failed) · 2 unverified
augment in 36 papers HorizonNet/inference.py ran MIT (permissive) · 6c798decc8af5b44 · report fixture: signature x_img:Tensor/4/float, flip:bool/0/bool, rotate:list/1/float · returned tuple · level recorded 2026-09-26
augment_undo HorizonNet/inference.py ran MIT (permissive) · d7030b9fc8555db4 · report fixture: signature x_imgs_augmented:Tensor/4/float, aug_type:list/1/str · returned ndarray · level recorded 2026-09-26
find_N_peaks HorizonNet/inference.py ran MIT (permissive) · 2c99a936790c4965 · report fixture: signature signal:ndarray/1/float, r:int/0/int, min_v:float/0/float, N:int/0/int · returned tuple · level recorded 2026-09-26
lr_pad HorizonNet/model.py ran · our draft was wrong fingerprinted MIT (permissive) · fb884f33b5fda8ea · report fixture: signature x:Tensor/4/float, padding:int/0/int · returned Tensor · level recorded 2026-09-22
sort_xy_filter_unique HorizonNet/dataset.py ran MIT (permissive) · 87dffac4821848bf · report fixture: signature xs:ndarray/1/float, ys:ndarray/1/float, y_small_first:bool/0/bool · returned tuple · level recorded 2026-09-26
tri2halfspace HorizonNet/eval_cuboid.py ran MIT (permissive) · 7525fc8039cc75b5 · report fixture: signature pa:ndarray/1/float, pb:ndarray/1/float, p:ndarray/1/float · returned list · level recorded 2026-09-26
xyzlst2halfspaces HorizonNet/eval_cuboid.py ran fingerprinted MIT (permissive) · 373920e32dc5fdb1 · report fixture: signature xyz_floor:ndarray/2/float, xyz_ceil:ndarray/2/float · returned ndarray · level recorded 2026-09-26
depth_loss_function loss.py unverified MIT (permissive) · dddbd5a319a669ff · report
make_image in 14 papers callbacks.py unverified MIT (permissive) · a5c4a0adfc21338d · report
rramjee/DenseDepth community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
DepthNorm Tensorflow/evaluate.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · 1852f926ecf3ccc4 · report fixture: signature x:Tensor/2/float, maxDepth:float/0/float · returned Tensor · level recorded 2026-09-22
predict in 126 papers Tensorflow/evaluate.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 6ce438ff124a45a8 · report fixture: signature model:StandInModel/0/?, images:ndarray/3/float, minDepth:int/0/int, maxDepth:int/0/int, batch_size:int/0/int · returned ndarray · level recorded 2026-09-22
scale_up Tensorflow/evaluate.py unverified GPL-3.0 (copyleft) · pointer only · 229418e47c5aa9bc · 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