SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.02410 · ICCV · 2023

Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image

Qi Qi, Jingyu Wang, Haifeng Sun, Jianxin Liao, Pengfei Ren, Chao Wen, Zhou Xue, Xiaozheng Zheng

arXiv · PDF · Open in the Atlas

Code that ran

11 of 11 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, 2 violated it and 3 have no contract verdict; 6 failures of our instrument; 0 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/2302.02410.json · badge: /api/ran/2302.02410.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
PengfeiRen96/DIR canonical (classifier label)
classifier basis not recorded on the link
11 ran · 0 no recorded run
FunctionStatusWhere it lives
adj_mx_from_edges Ran
ran on a synthesized input
PengfeiRen96/DIR/SemGCN/utils.py
code served (permissive licence) · get_code("341b55d9901d8be4")
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 2, dtype family float, shape (5, 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 numpy as np
import scipy.sparse as sp

torch.manual_seed(0)

# Create small test data for adj_mx_from_edges
num_pts = 5
edges = [
    [0, 1],
    [1, 2],
    [2, 3],
    [3, 4],
    [0, 4]
]

ARGS = {
    "num_pts": num_pts,
    "edges": edges,
    "sparse": False,
    "eye": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (5, 5) — shape (5, 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
cut_img Ran
ran on a synthesized input
PengfeiRen96/DIR/dataset/dataset_utils.py
code served (permissive licence) · get_code("cb4d572ce42dcb08")
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. 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 numpy as np
import cv2 as cv

# Create small valid arguments for cut_img function

# Create a small dummy image (256x256, 3-channel BGR)
img1 = np.random.randint(0, 256, (256, 256, 3), dtype=np.uint8)
img2 = np.random.randint(0, 256, (256, 256, 3), dtype=np.uint8)
img_list = [img1, img2]

# Create 2D labels - list of 2D point arrays (N points x 2 coordinates)
# Each label2d should have shape (num_points, 2)
label2d_1 = np.array([[50.0, 60.0], [100.0, 120.0], [80.0, 90.0]], dtype=np.float32)
label2d_2 = np.array([[55.0, 65.0], [105.0, 125.0], [85.0, 95.0]], dtype=np.float32)
label2d_list = [label2d_1, label2d_2]

# Create a camera intrinsic matrix (3x3)
camera = np.array([
    [500.0, 0.0, 128.0],
    [0.0, 500.0, 128.0],
    [0.0, 0.0, 1.0]
], dtype=np.float32)

# Other parameters
radio = 0.7
img_size = 256
transl = np.array([5.0, 10.0], dtype=np.float32)

ARGS = {
    'img_list': img_list,
    'label2d_list': label2d_list,
    'camera': camera,
    'radio': radio,
    'img_size': img_size,
    'transl': transl
}
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 tuple — a tuple output has no array shape of its own; none is 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
get_rotation_mat Ran
ran on a synthesized input
PengfeiRen96/DIR/dataset/dataset_utils.py
code served (permissive licence) · get_code("76299cb7b64c2844")
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 2, 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 math

def get_rotation_mat(center, theta=0):
    t = np.deg2rad(theta)
    rotationMat = np.zeros((3, 3), dtype='float32')
    rotationMat[0, 0] = math.cos(t)
    rotationMat[0, 1] = -math.sin(t)
    rotationMat[1, 0] = math.sin(t)
    rotationMat[1, 1] = math.cos(t)
    rotationMat[2, 2] = 1.0
    t = np.matmul(np.identity(3, dtype='float32') - rotationMat, center)
    rotationMat[0, 2] = t[0]
    rotationMat[1, 2] = t[1]
    return rotationMat

# Construct arguments
center = np.array([1.5, 2.5, 1.0], dtype='float32')
theta = 45

ARGS = {
    'center': center,
    'theta': theta
}
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 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (no_result)
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_trans Ran
ran; our contract draft was wrong, not the code
PengfeiRen96/DIR/models/manolayer.py
pointer only (licence: MIT); the stored copy get_code serves, from yunminjin2/bitt, is pointer only (licence: GPL-3.0) · get_code("c31f0ea4fb88ecdc")
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 yunminjin2/bitt, and GPL-3.0, as GitHub detects it on that repository, 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.

iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PengfeiRen96/DIR/models/lovasz_loss.py
code served (permissive licence) · get_code("d94639b28b2134ff")
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 1, dtype family float, shape (4,) 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 torch

torch.manual_seed(0)

# Construct valid arguments for the iou function
# preds: prediction array/tensor with class indices
# labels: ground truth array/tensor with class indices
# C: number of classes
# EMPTY: value to return for empty unions (default 1.0)
# ignore: class index to ignore (default None)
# per_image: whether to compute per-image IoU (default False)

# Create small prediction and label arrays
# Using shape (2, 4) - batch of 2, spatial dimension of 4
preds = np.array([[0, 1, 2, 3],
                   [1, 2, 0, 1]], dtype=np.int64)

labels = np.array([[0, 1, 1, 3],
                    [1, 2, 2, 1]], dtype=np.int64)

# Number of classes
C = 4

# EMPTY value for classes with no union
EMPTY = 1.0

# Class to ignore during computation
ignore = None

# Whether to compute per-image IoU
per_image = False

ARGS = {
    "preds": preds,
    "labels": labels,
    "C": C,
    "EMPTY": EMPTY,
    "ignore": ignore,
    "per_image": per_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) 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
iou_binary Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PengfeiRen96/DIR/models/lovasz_loss.py
code served (permissive licence) · get_code("1211530cd527bd0b")
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 float, 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 numpy as np

def isnan(x):
    return x != x

def mean(l, ignore_nan=False, empty=0):
    """
    nanmean compatible with generators.
    """
    l = iter(l)
    if ignore_nan:
        from itertools import filterfalse
        l = filterfalse(isnan, l)
    try:
        n = 1
        acc = next(l)
    except StopIteration:
        if empty == 'raise':
            raise ValueError('Empty mean')
        return empty
    for n, v in enumerate(l, 2):
        acc += v
    if n == 1:
        return acc
    return acc / n

def iou_binary(preds, labels, EMPTY=1.0, ignore=None, per_image=True):
    """
    IoU for foreground class
    binary: 1 foreground, 0 background
    """
    if not per_image:
        preds, labels = ((preds,), (labels,))
    ious = []
    for pred, label in zip(preds, labels):
        intersection = ((label == 1) & (pred == 1)).sum()
        union = ((label == 1) | (pred == 1) & (label != ignore)).sum()
        if not union:
            iou = EMPTY
        else:
            iou = float(intersection) / float(union)
        ious.append(iou)
    iou = mean(ious)
    return 100 * iou

# Setup code
np.random.seed(0)

# Create small prediction and label arrays for binary segmentation
# Shape: (height=4, width=3) for two images
preds_img1 = np.array([[0, 1, 1],
                       [1, 1, 0],
                       [0, 1, 1],
                       [1, 0, 0]], dtype=np.int32)

labels_img1 = np.array([[0, 1, 0],
                        [1, 1, 1],
                        [0, 1, 0],
                        [1, 0, 1]], dtype=np.int32)

preds_img2 = np.array([[1, 1, 0],
                       [0, 1, 1],
                       [1, 1, 0],
                       [0, 0, 1]], dtype=np.int32)

labels_img2 = np.array([[1, 0, 0],
                        [0, 1, 1],
                        [1, 0, 0],
                        [0, 1, 1]], dtype=np.int32)

# Arguments for iou_binary function
ARGS = {
    'preds': np.array([preds_img1, preds_img2]),
    'labels': np.array([labels_img1, labels_img2]),
    'EMPTY': 1.0,
    'ignore': 0,
    'per_image': True,
}
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 float, 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
lovasz_grad Ran
ran, violated the contract we drafted
PengfeiRen96/DIR/models/lovasz_loss.py
code served (permissive licence) · get_code("e85b5d21dc5b8382")
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 1, dtype family float, shape (4,) 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)

# gt_sorted should be a 1D tensor of binary/boolean values
# representing ground truth sorted by some error metric
# The function expects a tensor with sum(), float(), cumsum() methods
gt_sorted = torch.tensor([0, 0, 1, 1], dtype=torch.long)

ARGS = {
    "gt_sorted": gt_sorted
}
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 1, dtype family float, shape (4,) — shape (4,) 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
normalize Ran
ran, violated the contract we drafted
PengfeiRen96/DIR/SemGCN/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from songw-sw/x-fnc, is pointer only (licence: NONE) · get_code("aa9c29936dee40a7")
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 songw-sw/x-fnc, 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. A run is recorded.

rodrigues_batch Ran
ran; our contract draft was wrong, not the code
PengfeiRen96/DIR/models/manolayer.py
pointer only (licence: MIT); the stored copy get_code serves, from yunminjin2/bitt, is pointer only (licence: GPL-3.0) · get_code("3830b5b96e0ecb42")
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 yunminjin2/bitt, and GPL-3.0, as GitHub detects it on that repository, 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.

sparse_mx_to_torch_sparse_tensor Ran
ran; our contract draft was wrong, not the code
PengfeiRen96/DIR/SemGCN/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from yimengmin/geometricscatteringmaximalclique, is pointer only (licence: NONE) · get_code("bdc1f1dad6d978e7")
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 yimengmin/geometricscatteringmaximalclique, 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. A run is recorded.

vec2mat Ran
ran; our contract draft was wrong, not the code
PengfeiRen96/DIR/models/manolayer.py
pointer only (licence: MIT); the stored copy get_code serves, from yunminjin2/bitt, is pointer only (licence: GPL-3.0) · get_code("69bf838cdc7a5c19")
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 yunminjin2/bitt, and GPL-3.0, as GitHub detects it on that repository, 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.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 3 the same month, 8 later) and 3 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
lovasz_grad 40 other papers
16 dated earlier, 1 the same month, 23 later · 1 only as an assembly brick
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
and 37 more not named here
sparse_mx_to_torch_sparse_tensor 32 other papers
13 dated earlier, 19 later · 4 only as an assembly brick
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1902.07153 (2019-02)
Simplifying Graph Convolutional Networks
2002.01633 (2020-02)
Structural Deep Clustering Network
and 29 more not named here
iou 24 other papers
9 dated earlier, 1 the same month, 14 later
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
2003.10778 (2020-03)
PanNuke Dataset Extension, Insights and Baselines
and 21 more not named here
iou_binary 24 other papers
9 dated earlier, 1 the same month, 14 later
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
2003.10778 (2020-03)
PanNuke Dataset Extension, Insights and Baselines
and 21 more not named here
normalize 24 other papers
15 dated earlier, 9 later
1609.02907 (2016-09)
Semi-Supervised Classification with Graph Convolutional Networks
1803.03735 (2018-03)
Attention-based Graph Neural Network for Semi-supervised Learning
1805.09112 (2018-05)
Hyperbolic Neural Networks
and 21 more not named here
rodrigues_batch 2 other papers
2 later
2309.09301 (2023-09)
RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation
2403.08262 (2024-03)
BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image
get_trans 1 other paper
1 later
2403.08262 (2024-03)
BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image
vec2mat 1 other paper
1 later
2403.08262 (2024-03)
BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image

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

Reconstructing interacting hands from a single RGB image is a very challenging task. On the one hand, severe mutual occlusion and similar local appearance between two hands confuse the extraction of visual features, resulting in the misalignment of estimated hand meshes and the image. On the other hand, there are complex spatial relationship between interacting hands, which significantly increases the solution space of hand poses and increases the difficulty of network learning. In this paper, we propose a decoupled iterative refinement framework to achieve pixel-alignment hand reconstruction while efficiently modeling the spatial relationship between hands. Specifically, we define two feature spaces with different characteristics, namely 2D visual feature space and 3D joint feature space. First, we obtain joint-wise features from the visual feature map and utilize a graph convolution network and a transformer to perform intra-and inter-hand information interaction in the 3D joint feature space, respectively. Then, we project the joint features with global information back into the 2D visual feature space in an obfuscation-free manner and utilize the 2D convolution for pixel-wise enhancement. By performing multiple alternate enhancements in the two feature spaces, our method can achieve an accurate and robust reconstruction of interacting hands. Our method outperforms all existing two-hand reconstruction methods by a large margin on the InterHand2.6M dataset.

For agents

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

get_harvested_code_for_paper("2302.02410")
get_code_for_paper("2302.02410")
have("2302.02410")

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

curl https://syntology.ai/api/ran/2302.02410.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.02410.svg)](https://syntology.ai/paper/2302.02410)

Connect an agent — have() is free.