Browse State-of-the-Art › Disparity Estimation
Disparity Estimation
65 papers with code · 4 benchmarks · 4 datasets archive 2025-07-28
The Disparity Estimation is the task of finding the pixels in the multiscopic views that correspond to the same 3D point in the scene.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Sintel 4D LFV - ambushfight5 (1 row) | Two-stream CNN+CLSTM | Depth estimation from 4D light field videos | code | — | Compare |
| Sintel 4D LFV - thebigfight2 (1 row) | Two-stream CNN+CLSTM | Depth estimation from 4D light field videos | code | — | Compare |
| Sintel 4D LFV - bamboo3 (1 row) | Two-stream CNN+CLSTM | Depth estimation from 4D light field videos | code | — | Compare |
| Sintel 4D LFV - shaman2 (1 row) | Two-stream CNN+CLSTM | Depth estimation from 4D light field videos | 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
4 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 162 · with a code link: 65 · where Syntology ran a sample: 11 (9 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (11 of 162 tagged: 9 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 162, 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.
-
22 Aug 2021 4 repositories listed Syntology official (archive's flag): 1 ran · 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively.
-
8 Aug 2023 3 repositories listedA method to calibrate the inverse model is then proposed.
-
9 Apr 2021 3 repositories listed Syntology official: harvested, nothing ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified (of 21 harvested samples) · 5 pointer-only (licence)In this paper, we propose CFNet, a Cascade and Fused cost volume based network to improve the robustness of the stereo matching network.
-
7 Dec 2015 3 repositories listedBy combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
-
4 Feb 2023 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples) · 2 pointer-only (licence)While they attempt to increase the attack's efficiency, a further objective is to balance its effect, so that it acts on the entire image domain instead of isolated point-wise predictions.
-
8 Apr 2021 2 repositories listed Syntology official (archive's flag): 5 ran · 15 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified (of 28 harvested samples)Despite stereo matching accuracy has greatly improved by deep learning in the last few years, recovering sharp boundaries and high-resolution outputs efficiently remains challenging.
-
17 Mar 2021 2 repositories listedObject detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs.
-
23 Jun 2020 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)First, we construct combination volumes on the upper levels of the pyramid and develop a cost volume fusion module to integrate them for initial disparity estimation.
-
24 Mar 2020 2 repositories listedDeep neural networks (DNNs) have achieved great success in the area of computer vision.
-
9 Sep 2019 2 repositories listedHowever, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under…
-
4 Dec 2017 2 repositories listedThe second part performs matching cost calculation, matching cost aggregation and disparity calculation to estimate the initial disparity using shared features.
-
26 Jun 2025 1 repository listedIn the domain of cost-volume-based stereo matching, accurate disparity estimation depends heavily on large-scale cost volumes.
-
8 May 2025 1 repository listedHowever, DL-based disparity estimation methods are highly susceptible to distribution shifts and adversarial attacks, raising concerns about their reliability and generalization.
-
16 Jan 2025 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified (of 13 harvested samples) · 5 pointer-only (licence)Thus, to facilitate robust stereo matching with monocular depth cues, we incorporate a robust monocular relative depth model into the recurrent stereo-matching framework, building a new framework for depth foundation…
-
30 Sep 2024 1 repository listedWe introduce ImmersePro, an innovative framework specifically designed to transform single-view videos into stereo videos.
-
6 Sep 2024 1 repository listedFurthermore, we introduce a depth map compression model to minimize geometric redundancy across views, along with a multi-view sequence ordering strategy based on a defined distance measure between views to enhance…
-
1 Sep 2024 1 repository listedSimilar to a dual-pixel (DP) sensor, the phase shifting can be regarded as stereo disparity and utilized for depth estimation.
-
26 Aug 2024 1 repository listedMultispectral imaging is very beneficial in diverse applications, like healthcare and agriculture, since it can capture absorption bands of molecules in different spectral areas.
-
17 Jun 2024 1 repository listedOne approach for snapshot multispectral imaging, which is capable of recording multispectral videos, is by using camera arrays, where each camera records a different spectral band.
-
11 Jun 2024 1 repository listedInspired by the iteration-based methods, we propose a novel stepwise regression architecture.
-
10 Apr 2024 1 repository listed Syntology official (archive's flag): 17 ran · 17 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 0 unverified (of 17 harvested samples) · 6 pointer-only (licence)In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the…
-
28 Feb 2024 1 repository listedTo enhance geometric consistency, especially in low-texture regions, the estimated normal map is then leveraged to calculate a local affinity matrix, providing the residual learning with information about where the…
-
19 Feb 2024 1 repository listedTo address this challenge, we propose a method for generating ground-truth disparity maps directly from Light Detection and Ranging (LiDAR) and images to produce a large and diverse dataset for six aerial datasets…
-
15 Feb 2024 1 repository listedWe present a new approach to direct depth estimation for Spatial Augmented Reality (SAR) applications using event cameras.
-
3 Jan 2024 1 repository listedStereo matching and semantic segmentation are significant tasks in binocular satellite 3D reconstruction.
-
22 Dec 2023 1 repository listedDespite the remarkable progress facilitated by learning-based stereo-matching algorithms, the performance in the ill-conditioned regions, such as the occluded regions, remains a bottleneck.
-
14 Dec 2023 1 repository listedThe theoretical examination of the novel color agnostic method is completed by an extensive evaluation compared to state of the art including self-recorded multispectral data and a reference implementation.
-
13 Oct 2023 1 repository listedDifferent from most former disparity estimation methods that operate in a frame-wise manner, our network acquires disparity maps in a temporally incremental way.
-
1 Jun 2023 1 repository listedComputer vision systems that are deployed in safety-critical applications need to quantify their output uncertainty.
-
28 May 2023 1 repository listedTo address this issue and achieve a better trade-off between accuracy and efficiency, we propose an occlusion-aware cascade cost volume for LF depth (disparity) estimation.
-
22 Apr 2023 1 repository listed
-
15 Oct 2022 1 repository listed
-
12 Dec 2021 1 repository listed
-
24 Nov 2021 1 repository listed
-
11 Oct 2021 1 repository listed
-
2 Jun 2021 1 repository listed
-
25 May 2021 1 repository listed
-
15 Apr 2021 1 repository listed
-
18 Mar 2021 1 repository listed
-
1 Jan 2021 1 repository listed
-
5 Dec 2020 1 repository listed
-
18 Oct 2020 1 repository listed
-
14 Oct 2020 1 repository listed
-
6 Jul 2020 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 2 pointer-only (licence)
-
1 Jun 2020 1 repository listed
-
5 May 2020 1 repository listed
-
7 Apr 2020 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
29 Mar 2020 1 repository listed
-
1 Mar 2020 1 repository listed
-
7 Feb 2020 1 repository listed
-
21 Jan 2020 1 repository listed
-
20 Jan 2020 1 repository listed
-
20 Dec 2019 1 repository listed
-
27 Oct 2019 1 repository listed
-
20 Sep 2019 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
12 Apr 2019 1 repository listed Syntology 7 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; 1 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 1 pointer-only (licence)
-
25 Mar 2019 1 repository listed
-
5 Jul 2018 1 repository listed
-
19 May 2018 1 repository listed
-
8 May 2018 1 repository listed
-
18 Apr 2018 1 repository listed
-
5 Apr 2018 1 repository listed
-
14 Dec 2016 1 repository listed
-
13 Oct 2016 1 repository listed
-
RobuSTereo: Robust Zero-Shot Stereo Matching under Adverse Weather2 Jul 2025 0 repositories listed
-
DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning17 Jun 2025 0 repositories listed
-
Monocular Depth Guided Occlusion-Aware Disparity Refinement via Semi-supervised Learning in Laparoscopic Images13 May 2025 0 repositories listed
-
Eye2Eye: A Simple Approach for Monocular-to-Stereo Video Synthesis30 Apr 2025 0 repositories listed
-
All-directional Disparity Estimation for Real-world QPD Images1 Jan 2025 0 repositories listed
-
GBC-Splat: Generalizable Gaussian-Based Clothed Human Digitalization under Sparse RGB Cameras1 Jan 2025 0 repositories listed
-
Revisiting Disparity from Dual-Pixel Images: Physics-Informed Lightweight Depth Estimation6 Nov 2024 0 repositories listed
-
Analysis of different disparity estimation techniques on aerial stereo image datasets9 Oct 2024 0 repositories listed
-
EV-MGDispNet: Motion-Guided Event-Based Stereo Disparity Estimation Network with Left-Right Consistency10 Aug 2024 0 repositories listed
-
EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching31 Jul 2024 0 repositories listed
-
Stereo Risk: A Continuous Modeling Approach to Stereo Matching3 Jul 2024 0 repositories listed
-
Rectified Iterative Disparity for Stereo Matching16 Jun 2024 0 repositories listed
-
VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors4 Jun 2024 0 repositories listed
-
Multi-view Disparity Estimation Using a Novel Gradient Consistency Model27 May 2024 0 repositories listed
-
Iterative Occlusion-Aware Light Field Depth Estimation using 4D Geometrical Cues4 Mar 2024 0 repositories listed
-
Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging28 Feb 2024 0 repositories listed
-
Left-right Discrepancy for Adversarial Attack on Stereo Networks14 Jan 2024 0 repositories listed
-
Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context29 Nov 2023 0 repositories listed
-
SOccDPT: Semi-Supervised 3D Semantic Occupancy from Dense Prediction Transformers trained under memory constraints19 Nov 2023 0 repositories listed
-
Learning based Deep Disentangling Light Field Reconstruction and Disparity Estimation Application14 Nov 2023 0 repositories listed
-
Online Adaptive Disparity Estimation for Dynamic Scenes in Structured Light Systems13 Oct 2023 0 repositories listed
-
IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images29 Sep 2023 0 repositories listed
-
Video Frame Interpolation with Stereo Event and Intensity Camera17 Jul 2023 0 repositories listed
-
Continuous Cost Aggregation for Dual-Pixel Disparity Extraction13 Jun 2023 0 repositories listed
-
Unsupervised Light Field Depth Estimation via Multi-view Feature Matching with Occlusion Prediction20 Jan 2023 0 repositories listed
-
Regularizing disparity estimation via multi task learning with structured light reconstruction19 Jan 2023 0 repositories listed
-
Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image1 Jan 2023 0 repositories listed
-
Unsupervised Deep Asymmetric Stereo Matching With Spatially-Adaptive Self-Similarity1 Jan 2023 0 repositories listed
-
Disparity estimation for fisheye images with an application to intermediate view synthesis2 Dec 2022 0 repositories listed
-
Stereo Image Rain Removal via Dual-View Mutual Attention18 Nov 2022 0 repositories listed
-
Matching entropy based disparity estimation from light field28 Oct 2022 0 repositories listed
-
Fast Disparity Estimation from a Single Compressed Light Field Measurement22 Sep 2022 0 repositories listed
-
Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision12 Sep 2022 0 repositories listed
-
Perception-Oriented Stereo Image Super-Resolution14 Jul 2022 0 repositories listed
-
ORA3D: Overlap Region Aware Multi-view 3D Object Detection2 Jul 2022 0 repositories listed
Syntology lines on 12 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