SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.01724 · 2026

DenVisCoM: Dense Vision Correspondence Mamba for Efficient and Real-time Optical Flow and Stereo Estimation

Antitza Dantcheva, Abhijit Das, Tushar Anand, Maheswar Bora

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.01724.json · badge: /api/ran/2602.01724.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
vimstereo/DenVisCoM canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
bad_pixel_metric Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vimstereo/DenVisCoM/loss/stereo_metric.py
pointer only (licence: NONE) · get_code("cd39849ceb3c97b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_errors Ran
ran, honoured the contract we drafted
vimstereo/DenVisCoM/loss/depth_loss.py
pointer only (licence: NONE); the stored copy get_code serves, from nianticlabs/depth-hints, is pointer only (licence: NOASSERTION) · get_code("edd4f86e8f02732f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

d1_metric Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vimstereo/DenVisCoM/loss/stereo_metric.py
pointer only (licence: NONE) · get_code("3472053ffc0cd145")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

depth_grad_loss_func Ran
ran; our contract draft was wrong, not the code
vimstereo/DenVisCoM/loss/depth_loss.py
pointer only (licence: NONE) · get_code("8e127fda68e18297")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

epe_metric Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vimstereo/DenVisCoM/loss/stereo_metric.py
pointer only (licence: NONE) · get_code("de7db437cc7b6ca0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

flow_loss_func Ran
ran; our contract draft was wrong, not the code
vimstereo/DenVisCoM/loss/flow_loss.py
pointer only (licence: NONE) · get_code("715a9e324491547b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_depth_grad_loss Ran
ran; our contract draft was wrong, not the code
vimstereo/DenVisCoM/loss/depth_loss.py
pointer only (licence: NONE) · get_code("7724e6e792e75b5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

single_head_full_attention Ran
ran; our contract draft was wrong, not the code
vimstereo/DenVisCoM/DenVisCor/attention.py
pointer only (licence: NONE); the stored copy get_code serves, from ispc-lab/tma, is pointer only (licence: NONE) · get_code("52b500940a8025a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

single_head_full_attention_1d Ran
ran; our contract draft was wrong, not the code
vimstereo/DenVisCoM/DenVisCor/attention.py
pointer only (licence: NONE) · get_code("e886a8babb4916fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

single_head_split_window_attention Not yet run
unverified (harvested, no recorded run)
vimstereo/DenVisCoM/DenVisCor/attention.py
pointer only (licence: NONE) · get_code("9a948b3b755e6516")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vimstereo/DenVisCoM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
compute_errors 24 other papers
24 dated earlier
1609.03677 (2016-09)
Unsupervised Monocular Depth Estimation with Left-Right Consistency
1803.02276 (2018-03)
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
1806.01260 (2018-06)
Digging Into Self-Supervised Monocular Depth Estimation
and 21 more not named here
single_head_full_attention 6 other papers
6 dated earlier
2111.13680 (2021-11)
GMFlow: Learning Optical Flow via Global Matching
2303.11629 (2023-03)
TMA: Temporal Motion Aggregation for Event-based Optical Flow
2403.05327 (2024-03)
DiffSF: Diffusion Models for Scene Flow Estimation
and 3 more not named here
single_head_split_window_attention 3 other papers
3 dated earlier
2111.13680 (2021-11)
GMFlow: Learning Optical Flow via Global Matching
2410.13862 (2024-10)
DepthSplat: Connecting Gaussian Splatting and Depth
2503.01257 (2025-03)
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
d1_metric 1 other paper
1 dated earlier
2004.09548 (2020-04)
AANet: Adaptive Aggregation Network for Efficient Stereo Matching
epe_metric 1 other paper
1 dated earlier
2004.09548 (2020-04)
AANet: Adaptive Aggregation Network for Efficient Stereo Matching
flow_loss_func 1 other paper
1 dated earlier
2111.13680 (2021-11)
GMFlow: Learning Optical Flow via Global Matching
single_head_full_attention_1d 1 other paper
1 dated earlier
2410.13862 (2024-10)
DepthSplat: Connecting Gaussian Splatting and Depth

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we propose a novel Mamba block DenVisCoM, as well as a novel hybrid architecture specifically tailored for accurate and real-time estimation of optical flow and disparity estimation. Given that such multi-view geometry and motion tasks are fundamentally related, we propose a unified architecture to tackle them jointly. Specifically, the proposed hybrid architecture is based on DenVisCoM and a Transformer-based attention block that efficiently addresses real-time inference, memory footprint, and accuracy for at the same time for joint estimation of motion and 3D dense perception tasks. We extensively analyze the benchmark tradeoff of accuracy and real-time processing on a large number of datasets. Our experimental results and related analysis suggest that our proposed model can accurately estimate optical flow and disparity estimation in real time. All models and associated code are available at https://github.com/vimstereo/DenVisCoM.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.01724")
get_code_for_paper("2602.01724")
have("2602.01724")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.01724.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.01724.svg)](https://syntology.ai/paper/2602.01724)

Connect an agent — have() is free.