SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.01455 · 2021

Zero-Shot Text-Guided Object Generation with Dream Fields

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 8 have no contract verdict; 1 failure 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/2112.01455.json · badge: /api/ran/2112.01455.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
shengyu-meng/dreamfields-3D community (classifier label)
classifier basis not recorded on the link
9 ran · 1 no recorded run
FunctionStatusWhere it lives
get_encoder Ran
ran on a synthesized input
shengyu-meng/dreamfields-3D/encoding.py
code served (permissive licence) · get_code("72d37c800336a0ba")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define ARGS dict with all parameters for get_encoder
ARGS = {
    'encoding': 'frequency',
    'input_dim': 3,
    'multires': 6,
    'degree': 4,
    'num_levels': 16,
    'level_dim': 2,
    'base_resolution': 16,
    'log2_hashmap_size': 19,
    'desired_resolution': 2048,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
ashencoder, gridencoder, shencoder, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_view_direction Ran
ran on a synthesized input
shengyu-meng/dreamfields-3D/nerf/provider.py
code served (permissive licence) · get_code("08f9890fc9f0a74b")
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 1, dtype family int, shape (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 tensors for thetas and phis
# These need to have a .cpu() method and be convertible to numpy
# The function indexes them with shape[0], so batch dimension is important
batch_size = 2

# Create tensor of angles for phis (in range [0, 2*pi))
phis = torch.tensor([0.5, 2.0, 3.5, 5.5], dtype=torch.float32)

# Create tensor of angles for thetas (in range [0, pi])
thetas = torch.tensor([0.5, 1.0, 2.0, 2.5], dtype=torch.float32)

ARGS = {
    "thetas": thetas,
    "phis": phis,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (4,) — shape (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
mape_loss Ran
ran on a synthesized input
shengyu-meng/dreamfields-3D/loss.py
code served (permissive licence) · get_code("c6a72f3eb1bcaedc")
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 as nn

torch.manual_seed(0)

# Construct tiny tensors for pred and target
# The function computes: (pred - target).abs() * (1 / (target.abs() + 0.01))
# So both need to be tensors that support arithmetic operations

pred = torch.randn(2, 4)
target = torch.randn(2, 4)

ARGS = {
    "pred": pred,
    "target": target,
}
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
near_far_from_bound Ran
ran on a synthesized input
shengyu-meng/dreamfields-3D/nerf/renderer.py
code served (permissive licence) · get_code("58cb35f56b5a61a5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct small tensors for ray origins and directions
# batch_size=2, spatial_dim=3
rays_o = torch.randn(2, 3)  # Ray origins
rays_d = torch.randn(2, 3)  # Ray directions

# Normalize ray directions to be valid
rays_d = rays_d / (rays_d.norm(dim=-1, keepdim=True) + 1e-8)

# Bound parameter
bound = 1.0

# Type parameter
type_param = 'cube'

ARGS = {
    'rays_o': rays_o,
    'rays_d': rays_d,
    'bound': bound,
    'type': type_param,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
nerf_matrix_to_ngp Ran
ran on a synthesized input
shengyu-meng/dreamfields-3D/nerf/provider.py
code served (permissive licence) · get_code("ea0c1ea3b1314a9f")
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

# Create a valid 4x4 pose matrix (camera extrinsic matrix format)
pose = np.array([
    [1.0, 0.0, 0.0, 0.5],
    [0.0, 1.0, 0.0, 0.3],
    [0.0, 0.0, 1.0, 0.2],
    [0.0, 0.0, 0.0, 1.0]
], dtype=np.float32)

scale = 0.33

ARGS = {
    "pose": pose,
    "scale": scale
}
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
rand_poses Ran
ran on a synthesized input
shengyu-meng/dreamfields-3D/nerf/provider.py
code served (permissive licence) · get_code("6a0981461a74375d")
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
import numpy as np

torch.manual_seed(0)

ARGS = {
    'size': 2,
    'device': 'cpu',
    'radius': 1.0,
    'theta_range': [np.pi / 3, 2 * np.pi / 3],
    'phi_range': [0, 2 * np.pi],
    'randomize': True,
    'sample_size': 0,
    'index': 0,
}
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 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
rfft2d_freqs Ran
ran on a synthesized input
shengyu-meng/dreamfields-3D/nerf/bg_utils.py
code served (permissive licence) · get_code("66f0c9fbbdec320b")
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 (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)

# The function rfft2d_freqs takes two integer parameters: h (height) and w (width)
# It uses torch.fft.fftfreq to compute frequency components and returns a 2D frequency tensor
# We need small distinct sizes for h and w to make the shapes unambiguous

h = 4
w = 6

ARGS = {
    "h": h,
    "w": w,
}
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 (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
sample_pdf Ran
ran; our contract draft was wrong, not the code
shengyu-meng/dreamfields-3D/nerf/renderer.py
code served (permissive licence) · get_code("8ed7b9fc7f33d1dd")
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, 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)

# Construct arguments for sample_pdf
# The function expects:
# - bins: tensor of bin edges
# - weights: tensor of weights for each bin
# - n_samples: number of samples to draw
# - det: boolean for deterministic sampling

# Create small tensors with distinct dimensions
# bins: shape (batch=2, num_bins=5) - the bin edges
bins = torch.linspace(0, 1, steps=5).unsqueeze(0).expand(2, -1)

# weights: shape (batch=2, num_bins=4) - weights for each bin
# Note: num_bins for weights should be one less than bins since weights are for intervals
weights = torch.rand(2, 4)

# n_samples: number of samples to draw
n_samples = 3

# det: deterministic flag
det = False

ARGS = {
    "bins": bins,
    "weights": weights,
    "n_samples": n_samples,
    "det": det,
}
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, 3) — shape (2, 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
to_valid_rgb Ran
ran on a synthesized input
shengyu-meng/dreamfields-3D/nerf/bg_utils.py
code served (permissive licence) · get_code("0d8871eb5635a546")
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
import numpy as np

torch.manual_seed(0)

# Create a small test tensor with shape (2, 4, 3)
# where the innermost dimension is 3 (for RGB colors)
t = torch.randn(2, 4, 3, dtype=torch.float32)

ARGS = {
    "t": t,
    "decorrelated": False,
    "sigmoid": True,
}
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, 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
constrain_l_inf Not yet run
unverified (harvested, no recorded run)
shengyu-meng/dreamfields-3D/nerf/bg_utils.py
code served (permissive licence) · get_code("10b170fee86dc30d")
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, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 8 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
sample_pdf 10 other papers
1 dated earlier, 9 later · 1 only as an assembly brick
2110.00168 (2021-10)
Vision-Only Robot Navigation in a Neural Radiance World
2203.09517 (2022-03)
TensoRF: Tensorial Radiance Fields
2205.14870 (2022-05)
Compressible-composable NeRF via Rank-residual Decomposition
and 7 more not named here
nerf_matrix_to_ngp 1 other paper
1 later
aaai_25135 (2023 (year only))
One Is All: Bridging the Gap between Neural Radiance Fields Architectures with Progressive Volume Distillation

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 combine neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions. Our method, Dream Fields, can generate the geometry and color of a wide range of objects without 3D supervision. Due to the scarcity of diverse, captioned 3D data, prior methods only generate objects from a handful of categories, such as ShapeNet. Instead, we guide generation with image-text models pre-trained on large datasets of captioned images from the web. Our method optimizes a Neural Radiance Field from many camera views so that rendered images score highly with a target caption according to a pre-trained CLIP model. To improve fidelity and visual quality, we introduce simple geometric priors, including sparsity-inducing transmittance regularization, scene bounds, and new MLP architectures. In experiments, Dream Fields produce realistic, multi-view consistent object geometry and color from a variety of natural language captions.

For agents

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

get_harvested_code_for_paper("2112.01455")
get_code_for_paper("2112.01455")
have("2112.01455")

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

curl https://syntology.ai/api/ran/2112.01455.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.01455.svg)](https://syntology.ai/paper/2112.01455)

Connect an agent — have() is free.