SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.12140 · 2020

HITNet: Hierarchical Iterative Tile Refinement Network for Real-time 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; 0 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 0 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/2007.12140.json · badge: /api/ran/2007.12140.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
ibaiGorordo/HITNET-Stereo-Depth-estimation community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
meteorshowers/X-StereoLab port (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
ibaiGorordo/TFLite-HITNET-Stereo-depth-estimation community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
draw_depth Ran
ran on a synthesized input
ibaiGorordo/HITNET-Stereo-Depth-estimation/hitnet/utils_hitnet.py
code served (permissive licence) · get_code("8bb7fe039a0dd8bf")
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 int, shape (2, 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 cv2
import numpy as np

# Create a small depth map
# The function expects a 2D array-like object that supports:
# - Division operations
# - Indexing with boolean arrays
# - Being passed to cv2.convertScaleAbs
depth_map = np.array([
    [0.5, 1.2, 0.0, 2.1],
    [0.8, 1.5, 0.0, 1.9]
], dtype=np.float32)

# Set max_dist to a reasonable value for normalization
max_dist = 3.0

ARGS = {
    "depth_map": depth_map,
    "max_dist": max_dist
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (2, 4, 3) — shape (2, 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
draw_disparity Ran
ran on a synthesized input
ibaiGorordo/HITNET-Stereo-Depth-estimation/hitnet/utils_hitnet.py
code served (permissive licence) · get_code("c95dbd0cf81d5fa9")
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 int, shape (4, 3, 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 cv2

# Create a sample disparity map
# The function expects a numpy array that can be converted to uint8
# It will be normalized and color-mapped
disparity_map = np.random.rand(4, 3) * 255  # Small 4x3 disparity map with values in [0, 255]

ARGS = {
    "disparity_map": disparity_map
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (4, 3, 3) — shape (4, 3, 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
main_process Ran
ran, violated the contract we drafted
meteorshowers/X-StereoLab/tools/train_net_disp.py
code served (permissive licence) · get_code("06fca4c705811abe")
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 bool, ndim 0, dtype family float, 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 argparse

class Args:
    def __init__(self):
        self.multiprocessing_distributed = False
        self.rank = 0
        self.ngpus_per_node = 1

ARGS = {
    'args': Args()
}
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 bool, ndim 0, dtype family float, 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
wrap_frozen_graph Ran
ran on a synthesized input
ibaiGorordo/HITNET-Stereo-Depth-estimation/hitnet/utils_hitnet.py
code served (permissive licence) · get_code("713d88a6d30f8420")
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 WrappedFunction. The image it ran in was not recorded. If your copy returns the same type 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 tensorflow as tf
import numpy as np

# Create a simple frozen graph by building a basic model
def create_simple_frozen_graph():
    """Create a minimal frozen graph for testing."""
    # Disable v2 behavior to use v1 API
    tf.compat.v1.disable_eager_execution()
    
    # Create a simple graph with one operation
    graph = tf.compat.v1.Graph()
    with graph.as_default():
        # Create input placeholders
        input_x = tf.compat.v1.placeholder(tf.float32, shape=[None, 4], name='input_x')
        input_y = tf.compat.v1.placeholder(tf.float32, shape=[None, 3], name='input_y')
        
        # Simple operation: matrix multiplication
        weights = tf.constant(np.random.randn(4, 5).astype(np.float32), name='weights')
        output = tf.matmul(input_x, weights, name='output')
        
        # Convert graph to frozen graph definition
        with tf.compat.v1.Session(graph=graph) as sess:
            sess.run(tf.compat.v1.global_variables_initializer())
            graph_def = graph.as_graph_def()
    
    tf.compat.v1.reset_default_graph()
    tf.compat.v1.enable_eager_execution()
    return graph_def

# Generate the frozen graph
graph_def = create_simple_frozen_graph()

# Define input and output names as they would appear in the graph
inputs = ['input_x:0', 'input_y:0']
outputs = ['output:0']

ARGS = {
    'graph_def': graph_def,
    'inputs': inputs,
    'outputs': outputs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type WrappedFunction — a WrappedFunction output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a WrappedFunction output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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_img Not yet run
unverified (harvested, no recorded run)
ibaiGorordo/TFLite-HITNET-Stereo-depth-estimation/hitnet/utils_hitnet.py
code served (permissive licence) · get_code("21ab4fa6af33f75f")
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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
main_process 3 other papers
3 later
2301.02379 (2023-01)
CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior
2507.12001 (2025-07)
AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation

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

This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometric propagation and warping mechanisms to infer disparity hypotheses. To achieve a high level of accuracy, our network not only geometrically reasons about disparities but also infers slanted plane hypotheses allowing to more accurately perform geometric warping and upsampling operations. Our architecture is inherently multi-resolution allowing the propagation of information across different levels. Multiple experiments prove the effectiveness of the proposed approach at a fraction of the computation required by state-of-the-art methods. At the time of writing, HITNet ranks 1st-3rd on all the metrics published on the ETH3D website for two view stereo, ranks 1st on most of the metrics among all the end-to-end learning approaches on Middlebury-v3, ranks 1st on the popular KITTI 2012 and 2015 benchmarks among the published methods faster than 100ms.

For agents

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

get_harvested_code_for_paper("2007.12140")
get_code_for_paper("2007.12140")
have("2007.12140")

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

curl https://syntology.ai/api/ran/2007.12140.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.12140.svg)](https://syntology.ai/paper/2007.12140)

Connect an agent — have() is free.