Browse State-of-the-Art › Monocular Depth Estimation

Monocular Depth Estimation

430 papers with code · 24 benchmarks · 33 datasets archive 2025-07-28

Computer Vision

Monocular Depth Estimation is the task of estimating the depth value (distance relative to the camera) of each pixel given a single (monocular) RGB image. This challenging task is a key prerequisite for determining scene understanding for applications such as 3D scene reconstruction, autonomous driving, and AR. State-of-the-art methods usually fall into one of two categories: designing a complex network that is powerful enough to directly regress the depth map, or splitting the input into bins or windows to reduce computational complexity. The most popular benchmarks are the KITTI and NYUv2 datasets. Models are typically evaluated using RMSE or absolute relative error.

Source: Defocus Deblurring Using Dual-Pixel Data

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

25 leaderboard tables shown for this task, 24 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 25 until expanded.

Syntology 6 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): NYU-Depth V2 (4 judged, 0 placed), KITTI Eigen split (4 judged, 0 placed), ETH3D (1 judged, 0 placed), Hypersim (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
NYU-Depth V2 (85 rows) HybridDepth HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from... code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
KITTI Eigen split (79 rows) SPIDepth SPIdepth: Strengthened Pose Information for Self-supervised... code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified Compare
KITTI Eigen split unsupervised (55 rows) SPIdepth SPIdepth: Strengthened Pose Information for Self-supervised... code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified Compare
ETH3D (10 rows) Distill Any Depth Distill Any Depth: Distillation Creates a Stronger Monocular Depth... code — Compare
NYU-Depth V2 self-supervised (8 rows) IndoorDepth Deeper into Self-Supervised Monocular Indoor Depth Estimation code — Compare
Make3D (6 rows) SPIDepth SPIdepth: Strengthened Pose Information for Self-supervised... code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified Compare
Mid-Air Dataset (6 rows) M4Depth+U A technique to jointly estimate depth and depth uncertainty for... code — Compare
DDAD (4 rows) AFNet Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified Compare
IBims-1 (4 rows) Miangoleh et al. (SGR) Boosting Monocular Depth Estimation Models to High-Resolution via... code Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result Compare
SCARED-C (4 rows) AF-SfMLearner EndoDepth: A Benchmark for Assessing Robustness in Endoscopic... code — Compare
Cityscapes (3 rows) SwinMTL SwinMTL: A Shared Architecture for Simultaneous Depth Estimation... code — Compare
SUN-RGBD (3 rows) RPSF End-to-end Learning for Joint Depth and Image Reconstruction from... — — Compare
VA (Virtual Apartment) (3 rows) DistDepth Toward Practical Monocular Indoor Depth Estimation code — Compare
KITTI (2 rows) MonoViT MonoViT: Self-Supervised Monocular Depth Estimation with a Vision... code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
Middlebury 2014 (2 rows) Miangoleh et al. (MiDaS) Boosting Monocular Depth Estimation Models to High-Resolution via... code Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result Compare
Cityscapes 3D (1 row) TaskPrompter Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection,... code — Compare
DIML Outdoor (1 row) ScaleDepth-NK ScaleDepth: Decomposing Metric Depth Estimation into Scale... code — Compare
DIODE Indoor (1 row) ScaleDepth-NK ScaleDepth: Decomposing Metric Depth Estimation into Scale... code — Compare
DIODE Outdoor (1 row) ScaleDepth-NK ScaleDepth: Decomposing Metric Depth Estimation into Scale... code — Compare
Hypersim (1 row) ScaleDepth-NK ScaleDepth: Decomposing Metric Depth Estimation into Scale... code — Compare
KITTI Object Tracking Evaluation 2012 (1 row) PackNet-SfM 3D Packing for Self-Supervised Monocular Depth Estimation code — Compare
Matterport3D (1 row) NeWCRFs NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified Compare
UASOL (1 row) FCRN-DepthPrediction from Iro Laina et al. (2016) UASOL, a large-scale high-resolution outdoor stereo dataset — — Compare
Virtual KITTI 2 (1 row) ScaleDepth-NK ScaleDepth: Decomposing Metric Depth Estimation into Scale... code — Compare
MIX-6 (0 rows) no rows in the archive — —

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

33 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 33 until expanded.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 876 · with a code link: 430 · where Syntology ran a sample: 136 (117 with a run with no instrument failure, 19 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (136 of 876 tagged: 117 with a run with no instrument failure, 19 where every run was a failure of Syntology's instrument)

Page 1 of 9: papers 1 to 100 of 876, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 43 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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