SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.01618 · 2019

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 3 failures of our instrument; 3 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/1906.01618.json · badge: /api/ran/1906.01618.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
vsitzmann/scene-representation-networks community (classifier label)
classifier basis not recorded on the link
8 ran · 3 no recorded run
FunctionStatusWhere it lives
get_ray_directions_cam Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vsitzmann/scene-representation-networks/geometry.py
code served (permissive licence) · get_code("748b7ebd5f570deb")
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. 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 torch.nn as nn
from torch.nn import functional as F

torch.manual_seed(0)

# Create sample UV coordinates: (batch_size=2, num_samples=4, 2)
uv = torch.tensor([
    [[100.0, 150.0], [200.0, 250.0], [300.0, 350.0], [400.0, 450.0]],
    [[110.0, 160.0], [210.0, 260.0], [310.0, 360.0], [410.0, 460.0]]
], dtype=torch.float32)

# Create intrinsics matrix: (batch_size=2, 3, 3)
# Standard camera intrinsic matrix format
intrinsics = torch.tensor([
    [[500.0, 0.0, 320.0],
     [0.0, 500.0, 240.0],
     [0.0, 0.0, 1.0]],
    [[520.0, 0.0, 325.0],
     [0.0, 520.0, 245.0],
     [0.0, 0.0, 1.0]]
], dtype=torch.float32)

ARGS = {
    "uv": uv,
    "intrinsics": intrinsics
}
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
load_depth Ran
ran on a synthesized input
vsitzmann/scene-representation-networks/data_util.py
code served (permissive licence) · get_code("83666af2324d73b9")
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 3, dtype family float, shape (1, 32, 32) 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 cv2
import numpy as np
import tempfile
import os

# Create a temporary depth image file
temp_dir = tempfile.mkdtemp()
temp_path = os.path.join(temp_dir, "depth.png")

# Create a simple 16-bit depth image (grayscale)
depth_data = np.random.randint(0, 10000, size=(64, 64), dtype=np.uint16)
cv2.imwrite(temp_path, depth_data)

ARGS = {
    "path": temp_path,
    "sidelength": 32
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (1, 32, 32) — shape (1, 32, 32) 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_pose Ran
ran on a synthesized input
vsitzmann/scene-representation-networks/data_util.py
code served (permissive licence) · get_code("313ece65b8317903")
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 (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 numpy as np
import tempfile
import os

# Create a temporary file with pose data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "pose.txt")

# Write a single line with 16 space-separated values (4x4 matrix flattened)
pose_values = [str(float(i)) for i in range(16)]
with open(temp_file, 'w') as f:
    f.write(' '.join(pose_values))

ARGS = {
    'filename': temp_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 ndarray, ndim 2, dtype family float, shape (4, 4) — shape (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
load_rgb Ran
ran on a synthesized input
vsitzmann/scene-representation-networks/data_util.py
code served (permissive licence) · get_code("ae205850d108b184")
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 3, dtype family float, shape (3, 80, 80) 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 cv2
import numpy as np
import imageio
import skimage
import tempfile
import os

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple RGB image (100x80x3) using numpy
test_img = np.random.randint(0, 255, (100, 80, 3), dtype=np.uint8)
imageio.imwrite(temp_image_path, test_img)

ARGS = {
    "path": temp_image_path,
    "sidelength": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, imageio, numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (3, 80, 80) — shape (3, 80, 80) 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
parse_comma_separated_integers Ran
ran on a synthesized input
vsitzmann/scene-representation-networks/util.py
code served (permissive licence) · get_code("958a32edf6ef0539")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    "string": "1,2,3,4,5"
}
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 list, ndim 1, dtype family int — a list 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
partialclass Ran
ran; our contract draft was wrong, not the code
vsitzmann/scene-representation-networks/hyperlayers.py
code served (permissive licence) · get_code("61098cd5c9624563")
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 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 functools
import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple base class to demonstrate partialclass
class SimpleModel(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim):
        super().__init__()
        self.linear1 = nn.Linear(input_dim, hidden_dim)
        self.linear2 = nn.Linear(hidden_dim, output_dim)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Set up arguments for partialclass
# partialclass takes: cls, *args, **kwds
cls_arg = SimpleModel
args_tuple = (4, 8)  # input_dim, hidden_dim as positional args
kwds_dict = {"output_dim": 3}  # output_dim as keyword arg

ARGS = {
    "cls": cls_arg,
    "args": args_tuple,
    "kwds": kwds_dict
}
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 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
pick Ran
ran on a synthesized input
vsitzmann/scene-representation-networks/dataio.py
code served (permissive licence) · get_code("d6f32e468014bf11")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Construct arguments for the pick function
# The function takes a list and item_idcs, and returns selected items from the list

# Create a simple list with various types of items
test_list = [10, 20, 30, 40, 50]

# Create indices to pick from the list
item_idcs = [0, 2, 4]

ARGS = {
    "list": test_list,
    "item_idcs": item_idcs,
}
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 list, ndim 1, dtype family int — a list 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
reflect_vector_on_vector Ran
ran; our contract draft was wrong, not the code
vsitzmann/scene-representation-networks/geometry.py
code served (permissive licence) · get_code("54dc24b743feff79")
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 torch.nn.functional as F

torch.manual_seed(0)

# Create two small tensors for the reflection operation
# batch size: 2, dimension: 4
vector_to_reflect = torch.randn(2, 4)
reflection_axis = torch.randn(2, 4)

ARGS = {
    "vector_to_reflect": vector_to_reflect,
    "reflection_axis": reflection_axis,
}
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
clip_grad_norm_hook Not yet run
unverified (harvested, no recorded run)
vsitzmann/scene-representation-networks/custom_layers.py
code served (permissive licence) · get_code("2b5927b245fc6d2b")
How it ran

no invocation recorded.

convert_image Not yet run
unverified (harvested, no recorded run)
vsitzmann/scene-representation-networks/util.py
code served (permissive licence) · get_code("5fa28b6675135ab1")
How it ran

no invocation recorded.

get_latest_file Not yet run
unverified (harvested, no recorded run)
vsitzmann/scene-representation-networks/util.py
code served (permissive licence) · get_code("a7ef97b0f4462608")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 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
partialclass 5 other papers
5 later · 1 only as an assembly brick
2009.05475 (2020-09)
Adversarial score matching and improved sampling for image generation
2205.09853 (2022-05)
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation
2210.05927 (2022-10)
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
and 2 more not named here
get_ray_directions_cam 3 other papers
3 later
2206.01724 (2022-06)
SNAKE: Shape-aware Neural 3D Keypoint Field
2211.09786 (2022-11)
SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields
2309.05098 (2023-09)
3D Implicit Transporter for Temporally Consistent Keypoint Discovery
reflect_vector_on_vector 3 other papers
3 later
2206.01724 (2022-06)
SNAKE: Shape-aware Neural 3D Keypoint Field
2211.09786 (2022-11)
SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields
2309.05098 (2023-09)
3D Implicit Transporter for Temporally Consistent Keypoint Discovery
load_depth 1 other paper
1 later
2106.02634 (2021-06)
Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering
load_pose 1 other paper
1 later
2106.02634 (2021-06)
Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering

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

Unsupervised learning with generative models has the potential of discovering rich representations of 3D scenes. While geometric deep learning has explored 3D-structure-aware representations of scene geometry, these models typically require explicit 3D supervision. Emerging neural scene representations can be trained only with posed 2D images, but existing methods ignore the three-dimensional structure of scenes. We propose Scene Representation Networks (SRNs), a continuous, 3D-structure-aware scene representation that encodes both geometry and appearance. SRNs represent scenes as continuous functions that map world coordinates to a feature representation of local scene properties. By formulating the image formation as a differentiable ray-marching algorithm, SRNs can be trained end-to-end from only 2D images and their camera poses, without access to depth or shape. This formulation naturally generalizes across scenes, learning powerful geometry and appearance priors in the process. We demonstrate the potential of SRNs by evaluating them for novel view synthesis, few-shot reconstruction, joint shape and appearance interpolation, and unsupervised discovery of a non-rigid face model.

For agents

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

get_harvested_code_for_paper("1906.01618")
get_code_for_paper("1906.01618")
have("1906.01618")

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

curl https://syntology.ai/api/ran/1906.01618.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.01618.svg)](https://syntology.ai/paper/1906.01618)

Connect an agent — have() is free.