Browse State-of-the-Art › Depth Estimation

Depth Estimation

1,029 papers with code · 14 benchmarks · 77 datasets archive 2025-07-28

Computer Vision

Depth Estimation is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images. Traditional methods use multi-view geometry to find the relationship between the images. Newer methods can directly estimate depth by minimizing the regression loss, or by learning to generate a novel view from a sequence. The most popular benchmarks are KITTI and NYUv2. Models are typically evaluated according to a RMS metric.

Source: DIODE: A Dense Indoor and Outdoor DEpth Dataset

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

14 leaderboard tables shown for this task, 14 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 14 until expanded.

Syntology 5 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 (2 judged, 0 placed), ScanNetV2 (1 judged, 0 placed), DIODE (1 judged, 0 placed), ScanNet (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
Stanford2D3D Panoramic (18 rows) HiMODE HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model — — Compare
NYU-Depth V2 (17 rows) EVP EVP: Enhanced Visual Perception using Inverse Multi-Attentive... code — Compare
DCM (3 rows) Bhattacharjee et al. Estimating Image Depth in the Comics Domain code — Compare
eBDtheque (3 rows) Bhattacharjee et al. Estimating Image Depth in the Comics Domain code — Compare
ScanNetV2 (3 rows) Distill Any Depth Distill Any Depth: Distillation Creates a Stronger Monocular Depth... code — Compare
Cityscapes test (2 rows) SwinMTL SwinMTL: A Shared Architecture for Simultaneous Depth Estimation... code — Compare
DIODE (2 rows) AIP-Brown AI Playground: Unreal Engine-based Data Ablation Tool for Deep Learning code — Compare
KITTI 2015 (2 rows) H-Net (Ours) Full Eigen H-Net: Unsupervised Attention-based Stereo Depth Estimation... — — Compare
Mars DTM Estimation (2 rows) GLPDepth An Adversarial Generative Network Designed for High-Resolution... code — Compare
ScanNet (2 rows) Atlas (plain) Atlas: End-to-End 3D Scene Reconstruction from Posed Images code Syntology 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
4D Light Field Dataset (1 row) LFattNet Attention-based View Selection Networks for Light-field Disparity... code — Compare
KITTI Eigen split (1 row) LightDepth LightDepth: A Resource Efficient Depth Estimation Approach for... code — Compare
Matterport3D (1 row) UniFuse UniFuse: Unidirectional Fusion for 360° Panorama Depth Estimation code — Compare
Taskonomy (1 row) X-TC (Cross-Task Consistency) Robust Learning Through Cross-Task Consistency code — Compare

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

77 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 77 until expanded.

Subtasks archive 2025-07-28

10 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 2,454 · with a code link: 1,029 · where Syntology ran a sample: 292 (256 with a run with no instrument failure, 36 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (292 of 2,454 tagged: 256 with a run with no instrument failure, 36 where every run was a failure of Syntology's instrument)

Page 1 of 25: papers 1 to 100 of 2,454, 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 54 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