SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.11950 · ECCV · 2024

Temporally Consistent Stereo Matching

Yuwei Wu, Yunde Jia, Chengtang Yao, Jiaxi Zeng

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 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/2407.11950.json · badge: /api/ran/2407.11950.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
jiaxiZeng/Temporally-Consistent-Stereo-Matching canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
count_parameters Ran
ran, honoured the contract we drafted
jiaxiZeng/Temporally-Consistent-Stereo-Matching/evaluate_stereo.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
depth2disp Ran
ran; our contract draft was wrong, not the code
jiaxiZeng/Temporally-Consistent-Stereo-Matching/core/utils/geo_utils.py
code served (permissive licence) · get_code("58077120624c5300")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create tiny tensors matching the function signature
# depth: N,1,H,W where N=2 (batch), H=4, W=3
depth = torch.randn(2, 1, 4, 3, dtype=torch.float32) + 2.0  # Add 2.0 to avoid near-zero values

# baseline: should be a tensor that can be viewed as (-1, 1, 1, 1)
# The function does baseline.view(-1, 1, 1, 1), so it should have N elements
baseline = torch.tensor([0.12, 0.15], dtype=torch.float32)

# fx: N - focal length for each batch element
fx = torch.tensor([500.0, 520.0], dtype=torch.float32)

ARGS = {
    "depth": depth,
    "baseline": baseline,
    "fx": fx,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
disp2depth Ran
ran; our contract draft was wrong, not the code
jiaxiZeng/Temporally-Consistent-Stereo-Matching/core/utils/geo_utils.py
code served (permissive licence) · get_code("41b5d7f056eb7f26")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct valid arguments for disp2depth
# disp: N,1,H,W - disparity map with batch size 2, height 4, width 3
disp = torch.rand(2, 1, 4, 3) + 0.01  # Add offset to avoid very small values

# baseline: N,1 - baseline distance with batch size 2
baseline = torch.tensor([[0.1], [0.12]])

# fx: N - focal length with batch size 2
fx = torch.tensor([500.0, 520.0])

ARGS = {
    "disp": disp,
    "baseline": baseline,
    "fx": fx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
interp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiaxiZeng/Temporally-Consistent-Stereo-Matching/core/update.py
pointer only (licence: MIT); the stored copy get_code serves, from NVlabs/FoundationStereo, is pointer only (licence: NOASSERTION) · get_code("08bedbc0c0447f5d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from NVlabs/FoundationStereo, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

pool2x Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiaxiZeng/Temporally-Consistent-Stereo-Matching/core/update.py
pointer only (licence: MIT); the stored copy get_code serves, from NVlabs/FoundationStereo, is pointer only (licence: NOASSERTION) · get_code("25894ad2a73a8142")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from NVlabs/FoundationStereo, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

pool4x Ran
ran; our contract draft was wrong, not the code
jiaxiZeng/Temporally-Consistent-Stereo-Matching/core/update.py
pointer only (licence: MIT); the stored copy get_code serves, from bartn8/stereoanywhere, is pointer only (licence: NOASSERTION) · get_code("771e8ac695af28a9")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from bartn8/stereoanywhere, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

readDispBooster Ran
ran, honoured the contract we drafted
jiaxiZeng/Temporally-Consistent-Stereo-Matching/core/utils/frame_utils.py
code served (permissive licence) · get_code("37cde020fcf1c28c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import tempfile
import os

# Create a temporary .npy file with test data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_disp.npy")

# Create sample disparity data with some positive and negative values
disp_data = np.array([[-1.0, 2.5, 0.0],
                       [3.2, -0.5, 1.1]], dtype=np.float32)

# Save it as a numpy file
np.save(temp_file, disp_data)

ARGS = {
    "file_name": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
readPFM Ran
ran, honoured the contract we drafted
jiaxiZeng/Temporally-Consistent-Stereo-Matching/core/utils/frame_utils.py
code served (permissive licence) · get_code("7c3fbc1f552de802")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family float, shape (3, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import tempfile
import os

# Create a minimal valid PFM file
# PFM format: header (PF or Pf), width height, scale, then binary float data

def create_test_pfm():
    """Create a minimal valid PFM file for testing"""
    with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.pfm') as f:
        temp_path = f.name
        
        # Write header for color image (PF)
        f.write(b'PF\n')
        
        # Write dimensions: width=4, height=3
        f.write(b'4 3\n')
        
        # Write scale (positive means big-endian)
        f.write(b'1.0\n')
        
        # Write binary float data: 4*3*3 = 36 floats for color image
        data = np.ones((3, 4, 3), dtype='>f')  # big-endian floats
        data.tofile(f)
    
    return temp_path

# Create the test file
test_file_path = create_test_pfm()

ARGS = {
    'file': test_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (3, 4, 3) — shape (3, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
readFlow Not yet run
unverified (harvested, no recorded run)
jiaxiZeng/Temporally-Consistent-Stereo-Matching/core/utils/frame_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from NVIDIA/flownet2-pytorch, is pointer only (licence: NOASSERTION) · get_code("1662ea0b62b0229c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from NVIDIA/flownet2-pytorch, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

sequence_loss Not yet run
unverified (harvested, no recorded run)
jiaxiZeng/Temporally-Consistent-Stereo-Matching/train_stereo.py
code served (permissive licence) · get_code("a43e7cd33696630d")
How it ran

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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 1 the same month, 6 later) and 4 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
count_parameters 180 other papers
135 dated earlier, 6 the same month, 33 later, 6 same year, order not determinable · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
pool2x 8 other papers
4 dated earlier, 4 later · 1 only as an assembly brick
Zeng_Parameterized_Cost_Volume_for_Stereo_Matching_ICCV_2023_paper (2023 (year only))
Parameterized Cost Volume for Stereo Matching
2312.02155 (2023-12)
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
2403.00486 (2024-03)
Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
and 5 more not named here
readFlow 8 other papers
7 dated earlier, 1 later
1612.01925 (2016-12)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
2007.12622 (2020-07)
BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
2010.14851 (2020-10)
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
and 5 more not named here
interp 7 other papers
4 dated earlier, 3 later
Zeng_Parameterized_Cost_Volume_for_Stereo_Matching_ICCV_2023_paper (2023 (year only))
Parameterized Cost Volume for Stereo Matching
2312.02155 (2023-12)
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
2403.00486 (2024-03)
Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
and 4 more not named here
pool4x 6 other papers
4 dated earlier, 2 later
Zeng_Parameterized_Cost_Volume_for_Stereo_Matching_ICCV_2023_paper (2023 (year only))
Parameterized Cost Volume for Stereo Matching
2312.02155 (2023-12)
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
2403.00486 (2024-03)
Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
and 3 more not named here
readPFM 6 other papers
5 dated earlier, 1 later
2010.14851 (2020-10)
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
2104.13918 (2021-04)
High-Resolution Optical Flow from 1D Attention and Correlation
2109.15321 (2021-09)
Sensor-Guided Optical Flow
and 3 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

Stereo matching provides depth estimation from binocular images for downstream applications. These applications mostly take video streams as input and require temporally consistent depth maps. However, existing methods mainly focus on the estimation at the single-frame level. This commonly leads to temporally inconsistent results, especially in illposed regions. In this paper, we aim to leverage temporal information to improve the temporal consistency, accuracy, and efficiency of stereo matching. To achieve this, we formulate video stereo matching as a process of temporal disparity completion followed by continuous iterative refinements. Specifically, we first project the disparity of the previous timestamp to the current viewpoint, obtaining a semi-dense disparity map. Then, we complete this map through a disparity completion module to obtain a well-initialized disparity map. The state features from the current completion module and from the past refinement are fused together, providing a temporally coherent state for subsequent refinement. Based on this coherent state, we introduce a dual-space refinement module to iteratively refine the initialized result in both disparity and disparity gradient spaces, improving estimations in ill-posed regions. Extensive experiments demonstrate that our method effectively alleviates temporal inconsistency while enhancing both accuracy and efficiency. Currently, our method ranks second on the KITTI 2015 benchmark, while achieving superior efficiency compared to other state-of-the-art methods. The code is available at https://github.com/jiaxiZeng/Temporally-Consistent-Stereo-Matching.

For agents

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

get_harvested_code_for_paper("2407.11950")
get_code_for_paper("2407.11950")
have("2407.11950")

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

curl https://syntology.ai/api/ran/2407.11950.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.11950.svg)](https://syntology.ai/paper/2407.11950)

Connect an agent — have() is free.