SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.03560 · CVPR · 2023

DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium

Kyung-Soo Kim, Antyanta Bangunharcana, Ahmed Magd

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2304.03560.json · badge: /api/ran/2304.03560.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
antabangun/coex community
Papers with Code archive
9 ran · 3 no recorded run
FunctionStatusWhere it lives
AttentionCostVolume Ran
ran on a synthesized input · constructed an object; no result was computed
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("6c95e5ff30e64afb")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("18047492f074721c")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

BasicConv Ran
ran on a synthesized input · constructed an object; no result was computed
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("f71bfc07fbf21bdb")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

Conv2x Ran
ran on a synthesized input · constructed an object; no result was computed
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("c69dc4c45a088234")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

CostVolume Ran
ran on a synthesized input
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("eae7a9d6cf7abf20")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

FeatUp Ran
ran on a synthesized input · constructed an object; no result was computed
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("e1319551ee7b97c5")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

PSMBasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("d1af0c900f90009a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

Regression Ran
ran on a synthesized input · constructed an object; no result was computed
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("90e1616a76950902")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

channelAtt Ran
ran on a synthesized input · constructed an object; no result was computed
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("be8b7734951931e7")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

Aggregation Not yet run
unverified (harvested, no recorded run)
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("0c540f6ba2003637")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

CoEx Not yet run
unverified (harvested, no recorded run)
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("0fe16c5160b83416")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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.

Feature Not yet run
unverified (harvested, no recorded run)
antabangun/coex/models/stereo/CoEx.py
pointer only (licence: GPL-3.0) · get_code("8c44be6dba895858")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, antabangun/coex, is not in the permissive set Syntology serves inline. 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 11 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
BasicBlock 9 other papers
3 dated earlier, 6 later · 4 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2108.05722 (2021-08)
MT-ORL: Multi-Task Occlusion Relationship Learning
2303.15555 (2023-03)
Object Discovery from Motion-Guided Tokens
and 6 more not named here

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

Self-supervised multi-frame depth estimation achieves high accuracy by computing matching costs of pixel correspondences between adjacent frames, injecting geometric information into the network. These pixel-correspondence candidates are computed based on the relative pose estimates between the frames. Accurate pose predictions are essential for precise matching cost computation as they influence the epipolar geometry. Furthermore, improved depth estimates can, in turn, be used to align pose estimates. Inspired by traditional structure-from-motion (SfM) principles, we propose the DualRefine model, which tightly couples depth and pose estimation through a feedback loop. Our novel update pipeline uses a deep equilibrium model framework to iteratively refine depth estimates and a hidden state of feature maps by computing local matching costs based on epipolar geometry. Importantly, we used the refined depth estimates and feature maps to compute pose updates at each step. This update in the pose estimates slowly alters the epipolar geometry during the refinement process. Experimental results on the KITTI dataset demonstrate competitive depth prediction and odometry prediction performance surpassing published self-supervised baselines 1 .

For agents

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

get_harvested_code_for_paper("2304.03560")
get_code_for_paper("2304.03560")
have("2304.03560")

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

curl https://syntology.ai/api/ran/2304.03560.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.03560.svg)](https://syntology.ai/paper/2304.03560)

Connect an agent — have() is free.