SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.06704 · 2023

SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 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; 11 failures of our instrument; 5 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/2312.06704.json · badge: /api/ran/2312.06704.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
River-Zhang/SIFU canonical (classifier label)
classifier basis: census
13 ran · 5 no recorded run
FunctionStatusWhere it lives
build_smooth_conv3D Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/lib/common/seg3d_utils.py
code served (permissive licence) · get_code("c25753fc9d52f1fc")
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 Conv3d. 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)

ARGS = {
    "in_channels": 1,
    "out_channels": 1,
    "kernel_size": 3,
    "padding": 1,
}
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 Conv3d — a Conv3d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv3d 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
create_grid2D Ran
ran, honoured the contract we drafted
River-Zhang/SIFU/lib/common/seg3d_utils.py
code served (permissive licence) · get_code("c07f0db88d9cd069")
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 int, shape (25, 2) 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)

ARGS = {
    "min": 0,
    "max": 10,
    "steps": 5
}
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 int, shape (25, 2) — shape (25, 2) 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
create_grid3D Ran
ran, honoured the contract we drafted
River-Zhang/SIFU/lib/common/seg3d_utils.py
code served (permissive licence) · get_code("8e3d9f38a1b40efc")
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 int, shape (125, 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)

ARGS = {
    "min": 0,
    "max": 10,
    "steps": 5
}
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 int, shape (125, 3) — shape (125, 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
gen_mesh_color Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/apps/infer.py
code served (permissive licence) · get_code("3771ef371f90d296")
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, shape (50000, 3) as a later run recorded it. 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, 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
import torch.nn as nn

torch.manual_seed(0)

class SimpleNetG(nn.Module):
    def __init__(self, features_dim=256):
        super().__init__()
        self.features_G = features_dim
        self.linear = nn.Linear(features_dim + 3, 3)
    
    def query(self, in_feat, verts_tensor, calib_tensor, type='color'):
        batch_size = verts_tensor.shape[0]
        num_verts = verts_tensor.shape[2]
        feat_expanded = torch.randn(batch_size, in_feat, num_verts)
        verts_input = verts_tensor
        combined = torch.cat([feat_expanded, verts_input], dim=1)
        combined_flat = combined.permute(0, 2, 1)
        output = self.linear(combined_flat)
        output = output.permute(0, 2, 1).unsqueeze(0)
        return output

verts = torch.randn(50000, 3)
netG = SimpleNetG(features_dim=256)
cuda = 'cpu'
data = None

ARGS = {
    'verts': verts,
    'netG': netG,
    'cuda': cuda,
    'data': data
}
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 2, dtype family float, shape (50000, 3) — shape (50000, 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
gen_mesh_eval Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/lib/common/train_util.py
code served (permissive licence) · get_code("8f032be442a1aef5")
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. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Mock config object with resolution attribute
class MockOpt:
    def __init__(self):
        self.resolution = 32

# Mock neural network with filter method
class MockNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def filter(self, image_tensor):
        # filter is called but doesn't need to do anything meaningful
        pass

# Mock reconstruction_faster function (will be patched into the module)
def mock_reconstruction_faster(net, cuda, calib_tensor, resolution, b_min, b_max, use_octree=False):
    # Return mock verts and faces
    verts = torch.randn(10, 3)
    faces = torch.randint(0, 10, (5, 3))
    return verts, faces, None, None

# Create mock data dict
data = {
    'img': torch.randn(2, 4, 8, 8),  # batch=2, channels=4, spatial dims
    'calib': torch.randn(2, 3, 4),   # batch=2, calibration matrix 3x4
    'b_min': torch.tensor([-1.0, -1.0, -1.0]),
    'b_max': torch.tensor([1.0, 1.0, 1.0])
}

# Patch the reconstruction_faster into the module namespace
import sys
import types
mock_module = types.ModuleType('mock_reconstruction')
mock_module.reconstruction_faster = mock_reconstruction_faster
sys.modules['mock_reconstruction'] = mock_module

ARGS = {
    'opt': MockOpt(),
    'net': MockNet(),
    'cuda': 'cpu',
    'data': data,
    'resolution': None
}
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_calib Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/apps/infer.py
code served (permissive licence) · get_code("e23beb1e7eafd0a8")
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 numpy as np
import torch
import tempfile
import os

torch.manual_seed(0)

# Create a temporary calibration file with valid data
# The function expects:
# - rows 0-3: 4x4 extrinsic matrix
# - rows 4-7: 4x4 intrinsic matrix
temp_dir = tempfile.mkdtemp()
calib_path = os.path.join(temp_dir, "calib.txt")

# Create a 8x4 calibration matrix (4 rows extrinsic, 4 rows intrinsic)
calib_data = np.random.randn(8, 4).astype(float)
np.savetxt(calib_path, calib_data)

ARGS = {
    'calib_path': calib_path
}
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 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
load_segmentation Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/lib/common/cloth_extraction.py
pointer only (licence: MIT); the stored copy get_code serves, from YifYang993/HiLo, is pointer only (licence: NONE) · get_code("3433ad17bc7e6650")
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 YifYang993/HiLo, 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.

parse_args Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/lib/common/config.py
pointer only (licence: MIT); the stored copy get_code serves, from YifYang993/HiLo, is pointer only (licence: NONE) · get_code("27cd0667887a625b")
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 YifYang993/HiLo, 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.

rename Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/lib/common/train_util.py
code served (permissive licence) · get_code("66fb5ef9d96ef0a8")
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 torch

torch.manual_seed(0)

old_dict = {
    "layer1": torch.randn(2, 4),
    "layer2": torch.randn(3, 5),
    "bias": torch.randn(2)
}

old_name = "layer1"
new_name = "conv1"

ARGS = {
    "old_dict": old_dict,
    "old_name": old_name,
    "new_name": new_name
}
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 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
solid_angles Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/lib/common/render_utils.py
code served (permissive licence) · get_code("bd32d6f5d82a5a9e")
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 3, dtype family float, shape (2, 4, 5) as a later run recorded it. 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, 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)

# Construct arguments for solid_angles function
# points: BxQx3 - batch size B=2, Q query points=4, 3D coordinates
# triangles: BxFx3x3 - batch size B=2, F faces=5, 3 vertices per triangle, 3D coordinates
# thresh: float threshold

points = torch.randn(2, 4, 3)  # BxQx3: batch=2, queries=4, coords=3
triangles = torch.randn(2, 5, 3, 3)  # BxFx3x3: batch=2, faces=5, vertices=3, coords=3
thresh = 1e-08

ARGS = {
    "points": points,
    "triangles": triangles,
    "thresh": thresh,
}
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 3, dtype family float, shape (2, 4, 5) — shape (2, 4, 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
transform_to_tensor Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/lib/common/imutils.py
code served (permissive licence) · get_code("31b960f8590428bd")
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 Compose. 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 torchvision import transforms

torch.manual_seed(0)

ARGS = {
    "res": 224,
    "mean": [0.485, 0.456, 0.406],
    "std": [0.229, 0.224, 0.225],
    "is_tensor": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
vertex_colors_to_texture Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/apps/infer.py
code served (permissive licence) · get_code("b8a4086cbd7b040e")
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 Image. 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 torch
from PIL import Image

class MockVisual:
    def __init__(self, uv, vertex_colors):
        self.uv = uv
        self.vertex_colors = vertex_colors

class MockMesh:
    def __init__(self, uv, vertex_colors):
        self.visual = MockVisual(uv, vertex_colors)

# Create UV coordinates - normalized to [0, 1] range
# Shape: (num_vertices, 2)
uv_coords = np.array([
    [0.1, 0.2],
    [0.5, 0.5],
    [0.8, 0.9],
    [0.3, 0.7]
], dtype=np.float32)

# Create vertex colors as a torch tensor
# Shape: (num_vertices, 4) - RGBA, but function only uses first 3 channels
vertex_colors = torch.tensor([
    [255, 0, 0, 255],
    [0, 255, 0, 255],
    [0, 0, 255, 255],
    [255, 255, 0, 255]
], dtype=torch.uint8)

# Create mesh object with visual attributes
mesh = MockMesh(uv_coords, vertex_colors)

ARGS = {
    "mesh": mesh,
    "texture_size": (512, 512)
}
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 Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
winding_numbers Ran
ran; our contract draft was wrong, not the code
River-Zhang/SIFU/lib/common/render_utils.py
code served (permissive licence) · get_code("cd54a895a2ab8720")
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. 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, 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 math

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# points: BxQx3 where B=batch, Q=query points, 3=coordinates
# triangles: BxFx3x3 where B=batch, F=faces, 3=vertices per triangle, 3=coordinates per vertex

batch_size = 2
num_query_points = 4
num_triangles = 3
coord_dim = 3

# Create random points
points = torch.randn(batch_size, num_query_points, coord_dim)

# Create random triangles (vertices of triangles)
triangles = torch.randn(batch_size, num_triangles, 3, coord_dim)

# Create threshold
thresh = 1e-8

ARGS = {
    "points": points,
    "triangles": triangles,
    "thresh": thresh,
}
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
get_affine_matrix_box Not yet run
unverified (harvested, no recorded run)
River-Zhang/SIFU/lib/common/imutils.py
code served (permissive licence) · get_code("227a4974e3e6917b")
How it ran

no invocation recorded.

get_affine_matrix_wh Not yet run
unverified (harvested, no recorded run)
River-Zhang/SIFU/lib/common/imutils.py
code served (permissive licence) · get_code("00f9feda347a4ad9")
How it ran

no invocation recorded.

reshape_sample_tensor Not yet run
unverified (harvested, no recorded run)
River-Zhang/SIFU/lib/common/train_util.py
code served (permissive licence) · get_code("79509ef34e0af8e4")
How it ran

no invocation recorded.

smpl_to_recon_labels Not yet run
unverified (harvested, no recorded run)
River-Zhang/SIFU/lib/common/cloth_extraction.py
pointer only (licence: MIT); the stored copy get_code serves, from YifYang993/HiLo, is pointer only (licence: NONE) · get_code("32b523249d5d7868")
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 YifYang993/HiLo, 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.

update_cfg Not yet run
unverified (harvested, no recorded run)
River-Zhang/SIFU/lib/common/config.py
pointer only (licence: MIT); the stored copy get_code serves, from YifYang993/HiLo, is pointer only (licence: NONE) · get_code("938f7173c2e6ab9c")
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 YifYang993/HiLo, 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.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 12 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 0 the same month, 4 later) and 6 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
load_segmentation 3 other papers
2 dated earlier, 1 later
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
2404.04876 (2024-04)
HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models
parse_args 3 other papers
2 dated earlier, 1 later
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
2404.04876 (2024-04)
HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models
smpl_to_recon_labels 3 other papers
2 dated earlier, 1 later
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
2404.04876 (2024-04)
HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models
update_cfg 3 other papers
2 dated earlier, 1 later
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
2404.04876 (2024-04)
HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models
build_smooth_conv3D 2 other papers
2 dated earlier
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
create_grid2D 2 other papers
2 dated earlier
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
create_grid3D 2 other papers
2 dated earlier
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
reshape_sample_tensor 2 other papers
2 dated earlier
2108.08478 (2021-08)
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
solid_angles 2 other papers
2 dated earlier
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
winding_numbers 2 other papers
2 dated earlier
2308.08857 (2023-08)
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
gen_mesh_eval 1 other paper
1 dated earlier
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
rename 1 other paper
1 dated earlier
2309.13524 (2023-09)
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

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

Creating high-quality 3D models of clothed humans from single images for real-world applications is crucial. Despite recent advancements, accurately reconstructing humans in complex poses or with loose clothing from in-the-wild images, along with predicting textures for unseen areas, remains a significant challenge. A key limitation of previous methods is their insufficient prior guidance in transitioning from 2D to 3D and in texture prediction. In response, we introduce SIFU (Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction), a novel approach combining a Side-view Decoupling Transformer with a 3D Consistent Texture Refinement pipeline.SIFU employs a cross-attention mechanism within the transformer, using SMPL-X normals as queries to effectively decouple side-view features in the process of mapping 2D features to 3D. This method not only improves the precision of the 3D models but also their robustness, especially when SMPL-X estimates are not perfect. Our texture refinement process leverages text-to-image diffusion-based prior to generate realistic and consistent textures for invisible views. Through extensive experiments, SIFU surpasses SOTA methods in both geometry and texture reconstruction, showcasing enhanced robustness in complex scenarios and achieving an unprecedented Chamfer and P2S measurement. Our approach extends to practical applications such as 3D printing and scene building, demonstrating its broad utility in real-world scenarios. Project page https://river-zhang.github.io/SIFU-projectpage/ .

For agents

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

get_harvested_code_for_paper("2312.06704")
get_code_for_paper("2312.06704")
have("2312.06704")

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

curl https://syntology.ai/api/ran/2312.06704.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.06704.svg)](https://syntology.ai/paper/2312.06704)

Connect an agent — have() is free.