SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.01226 · 2023

Factor Fields: A Unified Framework for Neural Fields and Beyond

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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 3 have no contract verdict; 6 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/2302.01226.json · badge: /api/ran/2302.01226.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/factor-fields community (classifier label)
classifier basis not recorded on the link
9 ran · 1 no recorded run
FunctionStatusWhere it lives
dct_dict Ran
ran on a synthesized input
autonomousvision/factor-fields/models/FactorFields.py
code served (permissive licence) · get_code("796f33f768872d3f")
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 (8, 9) 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
import math

torch.manual_seed(0)

ARGS = {
    "n_atoms_fre": 4,
    "size": 3,
    "n_selete": 8,
    "dim": 2
}
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 (8, 9) — shape (8, 9) 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
eval_sh Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
autonomousvision/factor-fields/models/sh.py
pointer only (licence: MIT); the stored copy get_code serves, from pcl3dv/ov-nerf, is pointer only (licence: NONE) · get_code("db95ecdf5d4abe6b")
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 pcl3dv/ov-nerf, 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.

eval_sh_bases Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
autonomousvision/factor-fields/models/sh.py
code served (permissive licence) · get_code("caa9e209a9083a0f")
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, 9) 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 eval_sh_bases takes:
# - deg: int, SH max degree (0-4)
# - dirs: torch.Tensor of shape (..., 3) representing unit directions

# Create a small batch of unit direction vectors
# Shape: (2, 3) - batch of 2 directions, each with 3 components (x, y, z)
dirs = torch.tensor([
    [1.0, 0.0, 0.0],
    [0.0, 1.0, 0.0]
], dtype=torch.float32)

# Normalize to ensure they are unit directions
dirs = dirs / torch.norm(dirs, dim=-1, keepdim=True)

# Test with degree 2 (a middle value)
deg = 2

ARGS = {
    "deg": deg,
    "dirs": dirs
}
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, 9) — shape (2, 9) 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
grid_mapping Ran
ran on a synthesized input
autonomousvision/factor-fields/models/FactorFields.py
code served (permissive licence) · get_code("7a4a1fe69be15050")
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, 3, 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)

# Construct positions tensor: shape (batch_size, spatial_dim)
positions = torch.randn(2, 3)

# Construct freq_bands tensor: shape (num_freq_bands,)
freq_bands = torch.tensor([1.0, 2.0, 4.0, 8.0])

# Construct aabb (axis-aligned bounding box): list of two tensors [min, max]
# Each should have shape matching the spatial dimension of positions
aabb = [
    torch.tensor([0.0, 0.0, 0.0]),
    torch.tensor([10.0, 10.0, 10.0])
]

# basis_mapping parameter: one of 'sawtooth', 'triangle', 'sinc', 'trigonometric', 'x'
basis_mapping = 'sawtooth'

ARGS = {
    'positions': positions,
    'freq_bands': freq_bands,
    'aabb': aabb,
    'basis_mapping': basis_mapping
}
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, 3, 4) — shape (2, 3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
init_log Ran
ran; our contract draft was wrong, not the code
autonomousvision/factor-fields/utils.py
code served (permissive licence) · get_code("9a57689ea6df496c")
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)

log = {}
keys = ["loss", "accuracy", "epoch"]

ARGS = {
    "log": log,
    "keys": keys
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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
positional_encoding Ran
ran; our contract draft was wrong, not the code
autonomousvision/factor-fields/models/FactorFields.py
pointer only (licence: MIT); the stored copy get_code serves, from fengres/mixvoxels, is pointer only (licence: GPL-3.0) · get_code("11a10efa60767162")
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 fengres/mixvoxels, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

render_ray Ran
ran on a synthesized input
autonomousvision/factor-fields/renderer.py
code served (permissive licence) · get_code("f5313f1cee496199")
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. 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 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)

# Define a minimal factor_fields model that satisfies the function's usage
class FactorFields(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(10, 4)
    
    def forward(self, rays_chunk, is_train=False, white_bg=True, ndc_ray=False, N_samples=-1):
        # rays_chunk shape: (batch, 10) - minimal ray representation
        # Returns: (rgb_map, depth_map, coeff) where coeff is only used in training
        batch_size = rays_chunk.shape[0]
        rgb_map = torch.randn(batch_size, 3)
        depth_map = torch.randn(batch_size, 1)
        coeff = torch.randn(batch_size, 2) if is_train else torch.randn(batch_size, 2)
        return rgb_map, depth_map, coeff

# Create minimal ray tensor: (num_rays, ray_dim)
# Using 10 rays, 10-dimensional ray representation
rays = torch.randn(10, 10)

# Create factor_fields model
factor_fields = FactorFields()

ARGS = {
    'rays': rays,
    'factor_fields': factor_fields,
    'chunk': 4,
    'N_samples': -1,
    'ndc_ray': False,
    'white_bg': True,
    'is_train': False,
    'device': 'cpu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
imageio, 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
visualize_depth Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
autonomousvision/factor-fields/utils.py
code served (permissive licence) · get_code("a3e87fc7562ed971")
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 cv2
import torch
import numpy as np
from PIL import Image
import torchvision.transforms as T

torch.manual_seed(0)

# Create a small depth map (H=4, W=3)
depth_numpy = np.random.rand(4, 3) * 10.0
depth_numpy[0, 0] = 0.0  # Add a zero value to test nan_to_num

# Test with both numpy array and torch tensor
depth_input = torch.from_numpy(depth_numpy).float()

# minmax parameter - None or [min, max] tuple
minmax = None

# cmap parameter - OpenCV colormap
cmap = cv2.COLORMAP_JET

ARGS = {
    "depth": depth_input,
    "minmax": minmax,
    "cmap": cmap
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy, torch, torchvision — 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
visualize_depth_numpy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
autonomousvision/factor-fields/utils.py
code served (permissive licence) · get_code("f15b72957f9bb726")
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 cv2
import torch
import numpy as np

torch.manual_seed(0)

# Create a small depth map (H=4, W=3)
depth = np.random.rand(4, 3) * 10.0

# Define ARGS dict with all parameters
ARGS = {
    "depth": depth,
    "minmax": None,
    "cmap": cv2.COLORMAP_JET
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, 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
evaluation Not yet run
unverified (harvested, no recorded run)
autonomousvision/factor-fields/renderer.py
code served (permissive licence) · get_code("327ff36daa2346f2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
positional_encoding 17 other papers
5 dated earlier, 12 later · 2 only as an assembly brick
2205.14870 (2022-05)
Compressible-composable NeRF via Rank-residual Decomposition
2212.00190 (2022-12)
Mixed Neural Voxels for Fast Multi-view Video Synthesis
2301.02238 (2023-01)
HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
and 14 more not named here
eval_sh_bases 15 other papers
2 dated earlier, 13 later
2301.02238 (2023-01)
HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
2301.09632 (2023-01)
HexPlane: A Fast Representation for Dynamic Scenes
2303.03808 (2023-03)
Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis
and 12 more not named here
eval_sh 14 other papers
1 dated earlier, 13 later
2301.09632 (2023-01)
HexPlane: A Fast Representation for Dynamic Scenes
2303.03808 (2023-03)
Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis
2304.12461 (2023-04)
TensoIR: Tensorial Inverse Rendering
and 11 more not named here
visualize_depth_numpy 10 other papers
1 dated earlier, 9 later
2205.14870 (2022-05)
Compressible-composable NeRF via Rank-residual Decomposition
2303.03808 (2023-03)
Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis
2305.03462 (2023-05)
General Neural Gauge Fields
and 7 more not named here
init_log 9 other papers
1 dated earlier, 8 later
2205.14870 (2022-05)
Compressible-composable NeRF via Rank-residual Decomposition
2303.03808 (2023-03)
Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis
2305.03462 (2023-05)
General Neural Gauge Fields
and 6 more not named here
visualize_depth 8 other papers
1 dated earlier, 7 later
2205.14870 (2022-05)
Compressible-composable NeRF via Rank-residual Decomposition
2303.03808 (2023-03)
Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis
2305.14093 (2023-05)
Weakly Supervised 3D Open-vocabulary Segmentation
and 5 more not named here

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 Factor Fields, a novel framework for modeling and representing signals. Factor Fields decomposes a signal into a product of factors, each represented by a classical or neural field representation which operates on transformed input coordinates. This decomposition results in a unified framework that accommodates several recent signal representations including NeRF, Plenoxels, EG3D, Instant-NGP, and TensoRF. Additionally, our framework allows for the creation of powerful new signal representations, such as the "Dictionary Field" (DiF) which is a second contribution of this paper. Our experiments show that DiF leads to improvements in approximation quality, compactness, and training time when compared to previous fast reconstruction methods. Experimentally, our representation achieves better image approximation quality on 2D image regression tasks, higher geometric quality when reconstructing 3D signed distance fields, and higher compactness for radiance field reconstruction tasks. Furthermore, DiF enables generalization to unseen images/3D scenes by sharing bases across signals during training which greatly benefits use cases such as image regression from sparse observations and few-shot radiance field reconstruction.

For agents

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

get_harvested_code_for_paper("2302.01226")
get_code_for_paper("2302.01226")
have("2302.01226")

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

curl https://syntology.ai/api/ran/2302.01226.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.01226.svg)](https://syntology.ai/paper/2302.01226)

Connect an agent — have() is free.