SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.00638 · 2024

IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 3 failures of our instrument; 1 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/2409.00638.json · badge: /api/ran/2409.00638.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
gangweix/igev canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
gangweix/igev-plusplus canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
count_parameters Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from crisbodnar/ndp
pointer only · get_code("f6b944f50d3f15ae")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

fetch_optimizer Ran
ran; our contract draft was wrong, not the code
gangweix/igev-plusplus/train_stereo.py
code served (permissive licence) · get_code("5120c9f58c1f8e23")
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 1, 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 torch
import torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

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

model = SimpleModel()

class Args:
    def __init__(self):
        self.lr = 0.001
        self.wdecay = 0.01
        self.num_steps = 1000

args = Args()

ARGS = {
    'args': args,
    'model': model
}
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 tuple, ndim 1, 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
load_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gangweix/igev/IGEV-Stereo/demo_imgs.py
code served (permissive licence) · get_code("6c521de8b851930a")
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; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
from PIL import Image
import io

# Create a small test image in memory
# Create RGB image (3 channels, 4x5 size)
img_array = np.random.randint(0, 256, (4, 5, 3), dtype=np.uint8)
img = Image.fromarray(img_array, mode='RGB')

# Save to bytes buffer instead of file
img_buffer = io.BytesIO()
img.save(img_buffer, format='PNG')
img_buffer.seek(0)

# Create a temporary file-like object
class FakeImageFile:
    def __init__(self, buffer):
        self.buffer = buffer
    
    def __enter__(self):
        return self.buffer
    
    def __exit__(self, *args):
        pass

# For the function to work with Image.open(), we need an actual file path
# Since we can't do real I/O, we'll create a minimal mock that Image.open can handle
import tempfile
import os

# Create actual temporary file
temp_dir = tempfile.gettempdir()
temp_file = os.path.join(temp_dir, 'test_img_temp.png')
img.save(temp_file)

ARGS = {
    'imfile': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, 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 — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
sequence_loss Ran
ran; our contract draft was wrong, not the code
gangweix/igev/IGEV-Stereo/train_stereo.py
code served (permissive licence) · get_code("19dc732a081fc3f0")
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 1, 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Batch size: 2, Height: 4, Width: 3
batch_size = 2
height = 4
width = 3

# Create ground truth disparity with shape (batch, 1, height, width)
disp_gt = torch.randn(batch_size, 1, height, width)

# Create valid mask with shape (batch, height, width)
valid = torch.ones(batch_size, height, width)

# Create initial disparity prediction with shape (batch, 1, height, width)
disp_init_pred = torch.randn(batch_size, 1, height, width)

# Create a sequence of disparity predictions (3 predictions)
n_preds = 3
disp_preds = [torch.randn(batch_size, 1, height, width) for _ in range(n_preds)]

ARGS = {
    'disp_preds': disp_preds,
    'disp_init_pred': disp_init_pred,
    'disp_gt': disp_gt,
    'valid': valid,
    'loss_gamma': 0.9,
    'max_disp': 192
}
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 tuple, ndim 1, 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
sequence_loss Not yet run
unverified (harvested, no recorded run)
gangweix/igev-plusplus/train_stereo.py
code served (permissive licence) · get_code("15b7a863a68a8257")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 1 later) and 2 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
143 dated earlier, 4 the same month, 27 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
load_image 4 other papers
4 dated earlier
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2401.04861 (2024-01)
CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video
and 1 more not named here
fetch_optimizer 2 other papers
2 dated earlier
2109.07547 (2021-09)
RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching
2403.00486 (2024-03)
Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching

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 is a core component in many computer vision and robotics systems. Despite significant advances over the last decade, handling matching ambiguities in ill-posed regions and large disparities remains an open challenge. In this paper, we propose a new deep network architecture, called IGEV++, for stereo matching. The proposed IGEV++ constructs Multi-range Geometry Encoding Volumes (MGEV), which encode coarse-grained geometry information for ill-posed regions and large disparities, while preserving fine-grained geometry information for details and small disparities. To construct MGEV, we introduce an adaptive patch matching module that efficiently and effectively computes matching costs for large disparity ranges and/or ill-posed regions. We further propose a selective geometry feature fusion module to adaptively fuse multi-range and multi-granularity geometry features in MGEV. Then, we input the fused geometry features into ConvGRUs to iteratively update the disparity map. MGEV allows to efficiently handle large disparities and ill-posed regions, such as occlusions and textureless regions, and enjoys rapid convergence during iterations. Our IGEV++ achieves the best performance on the Scene Flow test set across all disparity ranges, up to 768px. Our IGEV++ also achieves state-of-the-art accuracy on the Middlebury, ETH3D, KITTI 2012, and 2015 benchmarks. Specifically, IGEV++ achieves a 3.23\% 2-pixel outlier rate (Bad 2.0) on the large disparity benchmark, Middlebury, representing error reductions of 31.9\% and 54.8\% compared to RAFT-Stereo and GMStereo, respectively. We also present a real-time version of IGEV++ that achieves the best performance among all published real-time methods on the KITTI benchmarks. The code is publicly available at https://github.com/gangweix/IGEV and https://github.com/gangweix/IGEV-plusplus.

For agents

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

get_harvested_code_for_paper("2409.00638")
get_code_for_paper("2409.00638")
have("2409.00638")

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

curl https://syntology.ai/api/ran/2409.00638.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.00638.svg)](https://syntology.ai/paper/2409.00638)

Connect an agent — have() is free.