SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.07372 · 2019

Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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, 1 violated it and 7 have no contract verdict; 0 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/1912.07372.json · badge: /api/ran/1912.07372.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
autonomousvision/differentiable_volumetric_rendering canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_reduction Ran
ran on a synthesized input
autonomousvision/differentiable_volumetric_rendering/im2mesh/losses.py
code served (permissive licence) · get_code("8e8b095bd78468a0")
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

torch.manual_seed(0)

# Create a small tensor for testing
tensor = torch.randn(2, 4)

# Define ARGS with all parameters
ARGS = {
    'tensor': tensor,
    'reduction_method': 'sum'
}
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
get_proposal_points_in_unit_cube Ran
ran on a synthesized input
autonomousvision/differentiable_volumetric_rendering/im2mesh/common.py
code served (permissive licence) · get_code("8f8fe08fe2f1fc7e")
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 torch

torch.manual_seed(0)

# Construct tensors
batch_size = 2
n_pts = 4
ray0 = torch.randn(batch_size, n_pts, 3)
ray_direction = torch.randn(batch_size, n_pts, 3)
ray_direction = ray_direction / torch.norm(ray_direction, dim=-1, keepdim=True)

# Define ARGS dict with all parameters
ARGS = {
    "ray0": ray0,
    "ray_direction": ray_direction,
    "padding": 0.1,
    "eps": 1e-06,
    "n_steps": 40,
}
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 — 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
is_url Ran
ran, violated the contract we drafted
autonomousvision/differentiable_volumetric_rendering/im2mesh/checkpoints.py
pointer only (licence: MIT); the stored copy get_code serves, from machineperceptionlab/cq-nir, is pointer only (licence: NONE) · get_code("71dbed7bd8b18214")
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 machineperceptionlab/cq-nir, 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.

l1_loss Ran
ran on a synthesized input
autonomousvision/differentiable_volumetric_rendering/im2mesh/losses.py
code served (permissive licence) · get_code("6d19709406fbc04b")
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

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# batch_size=2, feature_dim=4
val_gt = torch.randn(2, 4)
val_pred = torch.randn(2, 4)

ARGS = {
    'val_gt': val_gt,
    'val_pred': val_pred,
    'reduction_method': 'sum',
    'eps': 0.0,
    'sigma_pow': 1,
    'feat_dim': True,
}
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
l2_loss Ran
ran on a synthesized input
autonomousvision/differentiable_volumetric_rendering/im2mesh/losses.py
code served (permissive licence) · get_code("5598a5a212894e7e")
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

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# batch=2, dim=4
val_gt = torch.randn(2, 4)
val_pred = torch.randn(2, 4)

# reduction_method options: 'sum' or 'mean'
reduction_method = 'sum'

ARGS = {
    'val_gt': val_gt,
    'val_pred': val_pred,
    'reduction_method': reduction_method
}
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
load_config Ran
ran on a synthesized input
autonomousvision/differentiable_volumetric_rendering/im2mesh/config.py
code served (permissive licence) · get_code("841fbf5dbee0286c")
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 tempfile
import os
import yaml

# Create temporary YAML files for testing
temp_dir = tempfile.mkdtemp()

# Create a default config file
default_config_path = os.path.join(temp_dir, 'default_config.yaml')
with open(default_config_path, 'w') as f:
    yaml.dump({
        'learning_rate': 0.001,
        'batch_size': 32,
        'model': {
            'hidden_dim': 128,
            'num_layers': 2
        }
    }, f)

# Create a main config file that inherits from default
main_config_path = os.path.join(temp_dir, 'config.yaml')
with open(main_config_path, 'w') as f:
    yaml.dump({
        'inherit_from': default_config_path,
        'learning_rate': 0.01,
        'model': {
            'hidden_dim': 256
        }
    }, f)

# Create a standalone config file (no inheritance, no default)
standalone_config_path = os.path.join(temp_dir, 'standalone.yaml')
with open(standalone_config_path, 'w') as f:
    yaml.dump({
        'param1': 'value1',
        'param2': 42,
        'nested': {
            'key': 'val'
        }
    }, f)

ARGS = {
    'path': main_config_path,
    'default_path': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
rgb2gray Ran
ran on a synthesized input
autonomousvision/differentiable_volumetric_rendering/im2mesh/common.py
code served (permissive licence) · get_code("5cf2578f9a9a3c01")
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, 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)

# Create a small RGB tensor of shape (B, h, w, 3)
# B=2 (batch), h=4 (height), w=3 (width), 3 (RGB channels)
rgb = torch.rand(2, 4, 3, 3)

ARGS = {
    'rgb': rgb
}
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, 3) — shape (2, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sample_patch_points Ran
ran on a synthesized input
autonomousvision/differentiable_volumetric_rendering/im2mesh/common.py
code served (permissive licence) · get_code("c0436fa5619b233c")
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, 16, 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 = {
    "batch_size": 2,
    "n_points": 16,
    "patch_size": 2,
    "image_resolution": (8, 8),
    "continuous": True,
}
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, 16, 2) — shape (2, 16, 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

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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
is_url 12 other papers
12 later
2001.05119 (2020-01)
Learning multiview 3D point cloud registration
2003.04618 (2020-03)
Convolutional Occupancy Networks
2104.01148 (2021-04)
Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
and 9 more not named here
load_config 1 other paper
1 later
2209.14540 (2022-09)
NAF: Neural Attenuation Fields for Sparse-View CBCT 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

Learning-based 3D reconstruction methods have shown impressive results. However, most methods require 3D supervision which is often hard to obtain for real-world datasets. Recently, several works have proposed differentiable rendering techniques to train reconstruction models from RGB images. Unfortunately, these approaches are currently restricted to voxel- and mesh-based representations, suffering from discretization or low resolution. In this work, we propose a differentiable rendering formulation for implicit shape and texture representations. Implicit representations have recently gained popularity as they represent shape and texture continuously. Our key insight is that depth gradients can be derived analytically using the concept of implicit differentiation. This allows us to learn implicit shape and texture representations directly from RGB images. We experimentally show that our single-view reconstructions rival those learned with full 3D supervision. Moreover, we find that our method can be used for multi-view 3D reconstruction, directly resulting in watertight meshes.

For agents

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

get_harvested_code_for_paper("1912.07372")
get_code_for_paper("1912.07372")
have("1912.07372")

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

curl https://syntology.ai/api/ran/1912.07372.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.07372.svg)](https://syntology.ai/paper/1912.07372)

Connect an agent — have() is free.