SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.07191 · 2024

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

arXiv · PDF · Open in the Atlas

Code that ran

14 of 15 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; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 9 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/2404.07191.json · badge: /api/ran/2404.07191.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
tencentarc/instantmesh canonical (classifier label)
classifier basis: census
14 ran · 1 no recorded run
FunctionStatusWhere it lives
center_looking_at_camera_pose Ran
ran; our contract draft was wrong, not the code
tencentarc/instantmesh/src/utils/camera_util.py
code served (permissive licence) · get_code("9e6e6de54d3e0f7b")
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, 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 torch.nn.functional as F

torch.manual_seed(0)

# camera_position: can be (M, 3) or (3,)
# Test with (M, 3) case - batch of 2 cameras with 3D positions
camera_position = torch.tensor([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0]
], dtype=torch.float32)

# look_at: (3,) - optional, defaults to [0, 0, 0]
look_at = torch.tensor([0.5, 0.5, 0.5], dtype=torch.float32)

# up_world: (3,) - optional, defaults to [0, 0, 1]
up_world = torch.tensor([0.0, 1.0, 0.0], dtype=torch.float32)

ARGS = {
    "camera_position": camera_position,
    "look_at": look_at,
    "up_world": up_world,
}
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, 4) — shape (2, 4, 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_params Ran
ran, honoured the contract we drafted
tencentarc/instantmesh/src/utils/train_util.py
code served (permissive licence) · get_code("613acd72145a95f2")
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 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)

# Build a minimal nn.Module that has parameters
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,
    'verbose': False
}
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 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
get_obj_from_str Ran
ran; our contract draft was wrong, not the code
tencentarc/instantmesh/src/utils/train_util.py
code served (permissive licence) · get_code("221b2d116fdf1032")
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 type. 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 importlib
import torch
import torch.nn as nn

torch.manual_seed(0)

# The function get_obj_from_str takes a string like "module.path.ClassName"
# and returns the class/object by:
# 1. Splitting on the last dot to get module path and class name
# 2. Optionally reloading the module if reload=True
# 3. Importing the module and getting the attribute (class/object)

# We need to provide:
# - string: a valid module.class path that exists
# - reload: boolean flag

# Using a built-in class that's guaranteed to exist
string_value = "torch.nn.Linear"
reload_value = False

ARGS = {
    "string": string_value,
    "reload": reload_value,
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
loadobj Ran
ran; our contract draft was wrong, not the code
tencentarc/instantmesh/src/utils/mesh_util.py
code served (permissive licence) · get_code("3417c9784b2db355")
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 tempfile
import os

# Create a temporary OBJ file with valid mesh data
temp_dir = tempfile.mkdtemp()
meshfile = os.path.join(temp_dir, "test_mesh.obj")

with open(meshfile, 'w') as f:
    # Write vertices
    f.write("v 0.0 0.0 0.0\n")
    f.write("v 1.0 0.0 0.0\n")
    f.write("v 0.0 1.0 0.0\n")
    f.write("v 0.0 0.0 1.0\n")
    # Write faces (referencing vertices by index, 1-based)
    f.write("f 1 2 3\n")
    f.write("f 2 3 4\n")

ARGS = {
    "meshfile": meshfile
}
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 — 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
loadobjtex Ran
ran; our contract draft was wrong, not the code
tencentarc/instantmesh/src/utils/mesh_util.py
code served (permissive licence) · get_code("7dbbb5ea8f7fd9f1")
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 tempfile
import os

# Create a temporary OBJ file with valid mesh data
temp_dir = tempfile.mkdtemp()
meshfile = os.path.join(temp_dir, "test_mesh.obj")

obj_content = """# Simple cube mesh
v 0.0 0.0 0.0
v 1.0 0.0 0.0
v 1.0 1.0 0.0
v 0.0 1.0 0.0
v 0.0 0.0 1.0
v 1.0 0.0 1.0
v 1.0 1.0 1.0
v 0.0 1.0 1.0
vt 0.0 0.0
vt 1.0 0.0
vt 1.0 1.0
vt 0.0 1.0
vt 0.5 0.5
vt 0.75 0.75
f 1/1 2/2 3/3
f 1/1 3/3 4/4
f 5/5 6/2 7/3
f 5/5 7/3 8/4
"""

with open(meshfile, 'w') as f:
    f.write(obj_content)

ARGS = {
    "meshfile": meshfile
}
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 — 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
modulate Ran
ran; our contract draft was wrong, not the code
tencentarc/instantmesh/src/models/encoder/dino.py
code served (permissive licence) · get_code("03310bba324ae4fb")
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 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)

# Create small tensors for the modulate function
# x: input tensor with shape (batch_size, feature_dim)
x = torch.randn(2, 4)

# shift: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
shift = torch.randn(2)

# scale: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
scale = torch.randn(2)

ARGS = {
    "x": x,
    "shift": shift,
    "scale": scale,
}
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 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
pad_camera_extrinsics_4x4 Ran
ran, violated the contract we drafted
tencentarc/instantmesh/src/utils/camera_util.py
code served (permissive licence) · get_code("dd23b2696bcd01c0")
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, 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)

# Test case 1: 3D extrinsics (batch of 3x4 matrices)
extrinsics_3d = torch.randn(2, 3, 4)

ARGS = {
    "extrinsics": extrinsics_3d
}
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, 4) — shape (2, 4, 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
resize_foreground Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tencentarc/instantmesh/src/utils/infer_util.py
code served (permissive licence) · get_code("dbfd6882e8fac29b")
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 PIL.Image

# Create a simple RGBA image with a foreground object
# The function expects a PIL Image with 4 channels (RGBA)
# We'll create a 10x10 image with some non-transparent pixels in the center
image_array = np.zeros((10, 10, 4), dtype=np.uint8)
# Set some pixels in the center to be opaque (non-zero alpha)
image_array[3:7, 3:7, :3] = 200  # RGB channels
image_array[3:7, 3:7, 3] = 255   # Alpha channel (fully opaque)
# Rest of the image has alpha = 0 (transparent)

image = PIL.Image.fromarray(image_array, mode='RGBA')

ratio = 0.5

ARGS = {
    "image": image,
    "ratio": ratio
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — 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
scale_image Ran
ran, honoured the contract we drafted
tencentarc/instantmesh/zero123plus/model.py
code served (permissive licence) · get_code("3de799387827543b")
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 function takes a single parameter 'image' and performs scalar operations on it
# We need to provide a tensor that supports multiplication and division

image = torch.randn(2, 4)

ARGS = {
    "image": 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 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
scale_latents Ran
ran, honoured the contract we drafted
tencentarc/instantmesh/zero123plus/model.py
code served (permissive licence) · get_code("4a19e392bd2849ba")
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 scale_latents takes latents as input
# and performs arithmetic operations on it (subtraction and multiplication)
# This means latents should be a tensor that supports these operations

latents = torch.randn(2, 4)

ARGS = {
    "latents": latents
}
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
sdf_reg_loss_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tencentarc/instantmesh/src/model_mesh.py
code served (permissive licence) · get_code("fe52c543631a511f")
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 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 torch.nn.functional as F

torch.manual_seed(0)

# Construct arguments for sdf_reg_loss_batch
# sdf: tensor of shape (batch_size, num_vertices)
# all_edges: tensor of edge indices that will be reshaped to (-1,)

batch_size = 2
num_vertices = 4
num_edges = 3  # number of edges, each edge has 2 vertices

# Create sdf tensor: shape (batch_size, num_vertices)
sdf = torch.randn(batch_size, num_vertices)

# Create all_edges tensor
# When reshaped to (-1,), it should have even length (pairs of vertices)
# all_edges.reshape(-1) will flatten it, then we index sdf with these indices
# The reshape to (-1, 2) means we need all_edges to have shape (num_edges, 2)
# or similar that flattens to an even-length sequence
all_edges = torch.tensor([[0, 1], [1, 2], [2, 3]], dtype=torch.long)

ARGS = {
    "sdf": sdf,
    "all_edges": all_edges
}
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 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
spherical_camera_pose Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tencentarc/instantmesh/src/utils/camera_util.py
code served (permissive licence) · get_code("ca9edbb2178a5f5d")
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, 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)

# Create small numpy arrays for azimuths and elevations
azimuths = np.array([0.0, 45.0])  # 2 azimuth angles in degrees
elevations = np.array([0.0, 30.0])  # 2 elevation angles in degrees

ARGS = {
    "azimuths": azimuths,
    "elevations": elevations,
    "radius": 2.5
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 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
to_rgb_image Ran
ran; our contract draft was wrong, not the code
tencentarc/instantmesh/zero123plus/pipeline.py
code served (permissive licence) · get_code("2a705f9929a092ae")
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
from PIL import Image

# Create a small RGBA image for testing
rgba_data = numpy.zeros((4, 5, 4), dtype=numpy.uint8)
rgba_data[:, :, 0] = 255  # Red channel
rgba_data[:, :, 1] = 128  # Green channel
rgba_data[:, :, 2] = 64   # Blue channel
rgba_data[:, :, 3] = 200  # Alpha channel

rgba_image = Image.fromarray(rgba_data, 'RGBA')

ARGS = {
    'maybe_rgba': rgba_image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — 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
unscale_latents Ran
ran, honoured the contract we drafted
tencentarc/instantmesh/zero123plus/model.py
code served (permissive licence) · get_code("179671c9fed021ef")
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 takes latents (a tensor) and performs element-wise operations
# latents / 0.75 + 0.22
# So we need a tensor

latents = torch.randn(2, 4)

ARGS = {
    "latents": latents
}
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
instantiate_from_config Not yet run
unverified (harvested, no recorded run)
tencentarc/instantmesh/src/utils/train_util.py
code served (permissive licence) · get_code("ef52d142b2c30ac2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 9 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 7 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
modulate 101 other papers
24 dated earlier, 1 the same month, 75 later, 1 undated · 29 only as an assembly brick
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2203.10897 (2022-03)
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
and 98 more not named here
get_obj_from_str 54 other papers
27 dated earlier, 2 the same month, 24 later, 1 same year, order not determinable · 12 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2112.00384 (2021-12)
Exploration into Translation-Equivariant Image Quantization
and 51 more not named here
instantiate_from_config 24 other papers
16 dated earlier, 8 later · 7 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
and 21 more not named here
count_params 7 other papers
6 dated earlier, 1 later · 2 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
and 4 more not named here
resize_foreground 2 other papers
2 later
2406.15333 (2024-06)
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
2409.12957 (2024-09)
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
center_looking_at_camera_pose 1 other paper
1 later
2406.15333 (2024-06)
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
pad_camera_extrinsics_4x4 1 other paper
1 later
2406.15333 (2024-06)
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
scale_latents 1 other paper
1 dated earlier
2310.15110 (2023-10)
Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
unscale_latents 1 other paper
1 dated earlier
2310.15110 (2023-10)
Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model

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 InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability. By synergizing the strengths of an off-the-shelf multiview diffusion model and a sparse-view reconstruction model based on the LRM architecture, InstantMesh is able to create diverse 3D assets within 10 seconds. To enhance the training efficiency and exploit more geometric supervisions, e.g, depths and normals, we integrate a differentiable iso-surface extraction module into our framework and directly optimize on the mesh representation. Experimental results on public datasets demonstrate that InstantMesh significantly outperforms other latest image-to-3D baselines, both qualitatively and quantitatively. We release all the code, weights, and demo of InstantMesh, with the intention that it can make substantial contributions to the community of 3D generative AI and empower both researchers and content creators.

For agents

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

get_harvested_code_for_paper("2404.07191")
get_code_for_paper("2404.07191")
have("2404.07191")

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

curl https://syntology.ai/api/ran/2404.07191.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.07191.svg)](https://syntology.ai/paper/2404.07191)

Connect an agent — have() is free.