SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.04345 · ECCV · 2024

CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Images

Seongmin Lee, Hae-Gon Jeon, Jisu Shin, Junmyeong Lee, Min-Gyu Park, Ju-Mi Kang, Ju Yoon

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 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/2407.04345.json · badge: /api/ran/2407.04345.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
jsshin98/CanonicalFusion canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
angle_prior Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jsshin98/CanonicalFusion/utils/losses.py
code served (permissive licence) · get_code("0a589b69402596de")
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 (2, 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)

# The function expects a pose tensor with shape (batch_size, num_features)
# It indexes into columns [55-3=52, 58-3=55, 12-3=9, 15-3=12]
# So we need at least 56 columns (0-indexed up to 55)
# Create a small batch of 2 poses with 60 features
pose = torch.randn(2, 60)

ARGS = {
    "pose": pose
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
count_parameters Ran
ran, honoured the contract we drafted
jsshin98/CanonicalFusion/reconstructor/train_color2model.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
gmof Ran
ran, honoured the contract we drafted
jsshin98/CanonicalFusion/utils/losses.py
code served (permissive licence) · get_code("ac55fcb98792c961")
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 (2, 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
import numpy as np

torch.manual_seed(0)

# The gmof function takes two parameters: x and sigma
# Both are used in arithmetic operations (squaring, division, addition)
# They should be numeric tensors or arrays

# Create small tensors for x and sigma
x = torch.randn(2, 4)  # Small batch of 2, dimension 4
sigma = torch.randn(2, 4)  # Same shape as x for broadcasting

ARGS = {
    "x": x,
    "sigma": sigma,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
init_semantic_labels Ran
ran; our contract draft was wrong, not the code
jsshin98/CanonicalFusion/apps/data_loader.py
code served (permissive licence) · get_code("752ef5eedf81dab6")
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 dict. 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 os
import json
import tempfile
import numpy as np

# Create a temporary JSON file with semantic label structure
temp_dir = tempfile.mkdtemp()
label_file = os.path.join(temp_dir, "semantic_labels.json")

# Create a minimal but valid semantic label structure
label_data = {
    "leftHand": [0, 1, 2, 3, 4, 5],
    "rightHand": [10, 11, 12, 13, 14, 15],
    "leftForeArm": [2, 3, 4, 5, 100, 101],
    "rightForeArm": [12, 13, 14, 15, 102, 103],
    "head": [200, 201, 202],
    "eyeballs": [203, 204],
    "leftToeBase": [205],
    "rightToeBase": [206],
    "leftEye": [207],
    "rightEye": [208],
    "torso": list(range(300, 400)),
    "leftArm": list(range(400, 450)),
    "rightArm": list(range(450, 500))
}

with open(label_file, 'w') as f:
    json.dump(label_data, f)

ARGS = {
    "path2label": label_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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
init_variables Not yet run
unverified (harvested, no recorded run)
jsshin98/CanonicalFusion/reconstructor/train_color2model.py
code served (permissive licence) · get_code("529920c432b75fee")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
jsshin98/CanonicalFusion/reconstructor/train_color2model.py
code served (permissive licence) · get_code("bc70e3c7eb7c1354")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 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
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
gmof 2 other papers
2 dated earlier
2008.06133 (2020-08)
3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View
2105.09396 (2021-05)
Birds of a Feather: Capturing Avian Shape Models from Images

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

We present a novel framework for reconstructing animatable human avatars from multiple images, termed CanonicalFusion. Our central concept involves integrating individual reconstruction results into the canonical space. To be specific, we first predict Linear Blend Skinning (LBS) weight maps and depth maps using a shared-encoder-dual-decoder network, enabling direct canonicalization of the 3D mesh from the predicted depth maps. Here, instead of predicting high-dimensional skinning weights, we infer compressed skinning weights, i.e., 3-dimensional vector, with the aid of pre-trained MLP networks. We also introduce a forward skinning-based differentiable rendering scheme to merge the reconstructed results from multiple images. This scheme refines the initial mesh by reposing the canonical mesh via the forward skinning and by minimizing photometric and geometric errors between the rendered and the predicted results. Our optimization scheme considers the position and color of vertices as well as the joint angles for each image, thereby mitigating the negative effects of pose errors. We conduct extensive experiments to demonstrate the effectiveness of our method and compare our CanonicalFusion with state-of-the-art methods. Our source codes are available at https://github.com/jsshin98/CanonicalFusion.

For agents

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

get_harvested_code_for_paper("2407.04345")
get_code_for_paper("2407.04345")
have("2407.04345")

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

curl https://syntology.ai/api/ran/2407.04345.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.04345.svg)](https://syntology.ai/paper/2407.04345)

Connect an agent — have() is free.