SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.06264 · 2018

Hierarchical Discrete Distribution Decomposition for Match Density Estimation

arXiv · PDF · Open in the Atlas

Code that ran

6 of 14 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 4 have no contract verdict; 1 failure of our instrument; 8 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/1812.06264.json · badge: /api/ran/1812.06264.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
ucbdrive/hd3 canonical (classifier label)
classifier basis: census
5 ran · 8 no recorded run
lupvasile/hd3 canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
VGGEncoder Ran
ran on a synthesized input
ucbdrive/hd3/models/vgg.py
code served (permissive licence) · get_code("4fdf1ccac81de713")
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 VGG. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The VGGEncoder function takes 'planes' as its only parameter
# planes should be a list of integers representing output channels for each block

ARGS = {
    'planes': [64, 128, 256]
}
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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
ucbdrive/hd3/models/dla.py
code served (permissive licence) · get_code("dd1114865f06f0fd")
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 Conv2d. 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 torch
from torch import nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
flow_kitti_error Ran
ran on a synthesized input
ucbdrive/hd3/utils/flowlib.py
code served (permissive licence) · get_code("c79ac417345f891a")
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 numpy as np

np.random.seed(0)

# Create small flow maps (height=4, width=3)
height, width = 4, 3

# Ground truth horizontal and vertical flow
tu = np.random.randn(height, width).astype(np.float32)
tv = np.random.randn(height, width).astype(np.float32)

# Estimated horizontal and vertical flow (slightly different from ground truth)
u = tu + np.random.randn(height, width).astype(np.float32) * 0.1
v = tv + np.random.randn(height, width).astype(np.float32) * 0.1

# Mask: 1 for valid pixels, 0 for invalid
mask = np.ones((height, width), dtype=np.float32)
mask[0, 0] = 0  # Mark one pixel as invalid

ARGS = {
    "tu": tu,
    "tv": tv,
    "u": u,
    "v": v,
    "mask": mask,
}
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 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
flow_warp Ran
ran on a synthesized input
ucbdrive/hd3/models/hd3_ops.py
code served (permissive licence) · get_code("076593e69f1005ab")
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, 4, 3, 5) 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.functional as F

torch.manual_seed(0)

# Create a small image tensor [B, C, H, W]
# B=2 (batch), C=4 (channels), H=3 (height), W=5 (width)
x = torch.randn(2, 4, 3, 5)

# Create optical flow tensor [B, 2, H, W]
# 2 channels for (dx, dy) flow
flo = torch.randn(2, 2, 3, 5) * 0.5

# mul parameter controls whether to return output*mask or (output, mask)
mul = True

ARGS = {
    "x": x,
    "flo": flo,
    "mul": mul,
}
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, 4, 3, 5) — shape (2, 4, 3, 5) 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
get_target_size Ran
ran, honoured the contract we drafted
lupvasile/hd3/inference.py
code served (permissive licence) · get_code("e02bca604cfc58e7")
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 tuple, ndim 1, dtype family int; 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 math
import numpy as np

# The function get_target_size takes two parameters: H and W
# These are used as numeric values (integers or floats) representing height and width
# The function performs mathematical operations on them

H = 256
W = 384

ARGS = {
    "H": H,
    "W": W
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, dtype family int — 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
vector2density Ran
ran on a synthesized input
ucbdrive/hd3/models/hd3_ops.py
code served (permissive licence) · get_code("ea94ccf225af61f5")
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, 25, 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)

# For dim=2 case: vect should be shape (B, 2, H, W) - a 2D flow field
# For dim=1 case: vect should be shape (B, 1, H, W) - a disparity field
# We'll test with dim=2

B = 2
H = 4
W = 3
c = 2
dim = 2

# Create a small flow vector (B, dim, H, W)
vect = torch.randn(B, dim, H, W)

ARGS = {
    "vect": vect,
    "c": c,
    "dim": dim,
}
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, 25, 4, 3) — shape (2, 25, 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
DLAEncoder Not yet run
unverified (harvested, no recorded run)
ucbdrive/hd3/models/dla_up.py
code served (permissive licence) · get_code("688f35ca9f13c689")
How it ran

no invocation recorded.

EndPointError Not yet run
unverified (harvested, no recorded run)
ucbdrive/hd3/hd3losses.py
code served (permissive licence) · get_code("2f8bac97f40f84b7")
How it ran

no invocation recorded.

cupy_kernel Not yet run
unverified (harvested, no recorded run)
ucbdrive/hd3/models/correlation.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from xjtu-cvlab-lowlevel/rnn-mbp, is pointer only (licence: NONE) · get_code("262657b0ce1b117c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from xjtu-cvlab-lowlevel/rnn-mbp, and GitHub detected no licence in that repository 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.

density2vector Not yet run
unverified (harvested, no recorded run)
ucbdrive/hd3/models/hd3_ops.py
code served (permissive licence) · get_code("8f3bff158df466f7")
How it ran

no invocation recorded.

dla34 Not yet run
unverified (harvested, no recorded run)
ucbdrive/hd3/models/dla.py
code served (permissive licence) · get_code("782f63a5ade92085")
How it ran

no invocation recorded.

flow_error Not yet run
unverified (harvested, no recorded run)
ucbdrive/hd3/utils/flowlib.py
code served (permissive licence) · get_code("25417465cba28cc3")
How it ran

no invocation recorded.

readPFM Not yet run
unverified (harvested, no recorded run)
ucbdrive/hd3/utils/pfm.py
code served (permissive licence) · get_code("9c71f0f578921ed1")
How it ran

no invocation recorded.

read_flow Not yet run
unverified (harvested, no recorded run)
ucbdrive/hd3/utils/flowlib.py
code served (permissive licence) · get_code("d6e5f599346d62f8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 2 later) and 12 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
conv3x3 686 other papers
79 dated earlier, 6 the same month, 601 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
cupy_kernel 6 other papers
6 later
2003.04716 (2020-03)
Deep Blind Video Super-resolution
2004.02501 (2020-04)
Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
2006.13240 (2020-06)
Neural Non-Rigid Tracking
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

Explicit representations of the global match distributions of pixel-wise correspondences between pairs of images are desirable for uncertainty estimation and downstream applications. However, the computation of the match density for each pixel may be prohibitively expensive due to the large number of candidates. In this paper, we propose Hierarchical Discrete Distribution Decomposition (HD^3), a framework suitable for learning probabilistic pixel correspondences in both optical flow and stereo matching. We decompose the full match density into multiple scales hierarchically, and estimate the local matching distributions at each scale conditioned on the matching and warping at coarser scales. The local distributions can then be composed together to form the global match density. Despite its simplicity, our probabilistic method achieves state-of-the-art results for both optical flow and stereo matching on established benchmarks. We also find the estimated uncertainty is a good indication of the reliability of the predicted correspondences.

For agents

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

get_harvested_code_for_paper("1812.06264")
get_code_for_paper("1812.06264")
have("1812.06264")

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

curl https://syntology.ai/api/ran/1812.06264.json

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

[![Syntology run record](https://syntology.ai/api/ran/1812.06264.svg)](https://syntology.ai/paper/1812.06264)

Connect an agent — have() is free.