SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.06405 · ICCV · 2021

BARF : Bundle-Adjusting Neural Radiance Fields

Antonio Torralba, Chen-Hsuan Lin, Simon Lucey, Wei-Chiu Ma

arXiv · PDF · Open in the Atlas

Code that ran

12 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 9 failures of our instrument; 7 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/2104.06405.json · badge: /api/ran/2104.06405.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
chenhsuanlin/bundle-adjusting-NeRF canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
MQ66/gnerf community (classifier label)
classifier basis not recorded on the link
1 ran · 3 no recorded run
postech-cvlab/scnerf community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
CameraModel Ran
ran on a synthesized input · constructed an object; no result was computed
postech-cvlab/scnerf/model/camera_model.py
code served (permissive licence) · get_code("5c18825021f11763")
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 an instance of its own class, CameraModel: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

class Args:
    def __init__(self):
        self.camera_model = "perspective"
        self.ray_o_noise_scale = 0.1
        self.ray_d_noise_scale = 0.05
        self.extrinsics_noise_scale = 0.02
        self.intrinsics_noise_scale = 0.01

intrinsics = torch.eye(3, dtype=torch.float32)
intrinsics[0, 0] = 500.0  # fx
intrinsics[1, 1] = 500.0  # fy
intrinsics[0, 2] = 320.0  # cx
intrinsics[1, 2] = 240.0  # cy

extrinsics = torch.eye(4, dtype=torch.float32)

args = Args()

H = 8
W = 6

ARGS = {
    "intrinsics": intrinsics,
    "extrinsics": extrinsics,
    "args": 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 CameraModel — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CameraModel 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
blue Ran
ran; our contract draft was wrong, not the code
chenhsuanlin/bundle-adjusting-NeRF/util.py
code served (permissive licence) · get_code("2a69081f447e7ba0")
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 str. 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 termcolor

torch_imported = False
try:
    import torch
    torch_imported = True
except ImportError:
    pass

# Analyze the function signature and body
# The function takes:
# - message: converted to str, so any type works
# - **kwargs: dict of keyword arguments where True values add attributes

# The function uses kwargs.items() to iterate and check if v is True
# So we need to pass keyword arguments with boolean values

# Simple message
message = "Hello, World!"

# Keyword arguments with boolean values
# Some True, some False to test the filtering logic
kwargs_dict = {
    'bold': True,
    'dark': False,
    'underline': True,
    'blink': False,
    'reverse': True,
}

ARGS = {
    'message': message,
    **kwargs_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
termcolor, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_normalized_pixel_grid Ran
ran, honoured the contract we drafted
chenhsuanlin/bundle-adjusting-NeRF/warp.py
code served (permissive licence) · get_code("31d8aba2ce388395")
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, 12, 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)

class OptConfig:
    def __init__(self):
        self.H = 4
        self.W = 3
        self.device = 'cpu'
        self.batch_size = 2

opt = OptConfig()

ARGS = {
    'opt': opt
}
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, 12, 2) — shape (2, 12, 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
get_normalized_pixel_grid_crop Ran
ran, honoured the contract we drafted
chenhsuanlin/bundle-adjusting-NeRF/warp.py
code served (permissive licence) · get_code("7d12c0a3c8662e08")
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, 1280, 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)

class OptConfig:
    def __init__(self):
        self.H = 64
        self.W = 80
        self.H_crop = 32
        self.W_crop = 40
        self.batch_size = 2
        self.device = 'cpu'

opt = OptConfig()

ARGS = {
    'opt': opt
}
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, 1280, 2) — shape (2, 1280, 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
green Ran
ran; our contract draft was wrong, not the code
chenhsuanlin/bundle-adjusting-NeRF/util.py
code served (permissive licence) · get_code("a84f43afe520c054")
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 str. 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 termcolor

def green(message, **kwargs):
    return termcolor.colored(str(message), color='green', attrs=[k for k, v in kwargs.items() if v is True])

ARGS = {
    'message': 'Hello, World!',
    'bold': True,
    'dark': False,
    'underline': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
termcolor — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
load_options Ran
ran; our contract draft was wrong, not the code
chenhsuanlin/bundle-adjusting-NeRF/options.py
code served (permissive licence) · get_code("5dd98ac338acc206")
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 EasyDict. 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
from easydict import EasyDict as edict

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

# Create a parent config file
parent_config = {
    'model': {
        'type': 'resnet',
        'layers': 50
    },
    'training': {
        'lr': 0.001,
        'epochs': 100
    }
}

parent_file = os.path.join(temp_dir, 'parent_config.yaml')
with open(parent_file, 'w') as f:
    yaml.dump(parent_config, f)

# Create a child config file that overrides parent
child_config = {
    '_parent_': parent_file,
    'model': {
        'layers': 101
    },
    'training': {
        'lr': 0.0001
    }
}

child_file = os.path.join(temp_dir, 'child_config.yaml')
with open(child_file, 'w') as f:
    yaml.dump(child_config, f)

# Create a simple config file without parent
simple_config = {
    'batch_size': 32,
    'hidden_dim': 256,
    'dropout': 0.5
}

simple_file = os.path.join(temp_dir, 'simple_config.yaml')
with open(simple_file, 'w') as f:
    yaml.dump(simple_config, f)

ARGS = {
    'fname': simple_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict 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
parse_arguments Ran
ran; our contract draft was wrong, not the code
chenhsuanlin/bundle-adjusting-NeRF/options.py
code served (permissive licence) · get_code("c57c6e4ede0dc332")
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 EasyDict. 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 yaml
from easydict import EasyDict as edict

torch.manual_seed(0)

# The parse_arguments function takes a list of command-line style argument strings
# and parses them into a nested dictionary structure using dot notation.
# Examples of valid arguments:
# --key1.key2.key3=value
# --key1.key2.key3=
# --key1.key2.key3
# --key1.key2.key3!

ARGS = {
    'args': [
        '--model.name=resnet50',
        '--model.layers=50',
        '--training.lr=0.001',
        '--training.epochs=100',
        '--training.batch_size=',
        '--debug',
        '--verbose!',
        '--data.path=/tmp/data',
    ]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict, torch, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict 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
preprocess_vis_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
chenhsuanlin/bundle-adjusting-NeRF/util_vis.py
code served (permissive licence) · get_code("d61202a21ac5df1b")
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 4, dtype family float, shape (2, 3, 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 matplotlib.pyplot as plt

torch.manual_seed(0)

# Create a minimal opt object (dict works fine since the function doesn't call methods on it)
opt = {}

# Create a small test image tensor
# Shape: (batch_size=2, channels=1, height=4, width=3)
# Values in range [0, 1] for testing
images = torch.rand(2, 1, 4, 3)

# Define the from_range parameter
from_range = (0, 1)

# Define the colormap parameter
cmap = 'gray'

ARGS = {
    'opt': opt,
    'images': images,
    'from_range': from_range,
    'cmap': cmap
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 4, 3) — shape (2, 3, 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
red Ran
ran; our contract draft was wrong, not the code
chenhsuanlin/bundle-adjusting-NeRF/util.py
code served (permissive licence) · get_code("8733b61e389a9be2")
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 str. 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 termcolor

# The function takes:
# - message: any value that can be converted to string
# - **kwargs: keyword arguments where values are booleans to control text attributes

ARGS = {
    'message': 'This is a red message',
    'bold': True,
    'dark': False,
    'underline': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
termcolor — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
sample_pdf Ran
ran; our contract draft was wrong, not the code
MQ66/gnerf/model/rendering.py
code served (permissive licence) · get_code("ce678ba4bfcfef79")
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)

# Define dimensions
N_rays = 2
N_samples_ = 4  # number of coarse samples per ray - 2
N_importance = 3

# bins: (N_rays, N_samples_ + 1)
bins = torch.linspace(0, 1, N_samples_ + 1).unsqueeze(0).expand(N_rays, -1)
bins = bins + torch.randn(N_rays, N_samples_ + 1) * 0.01  # Add small noise for realism

# weights: (N_rays, N_samples_)
weights = torch.rand(N_rays, N_samples_)

# N_importance: number of samples to draw
N_importance = 3

# det: deterministic flag
det = False

# eps: small number to prevent division by zero
eps = 1e-05

ARGS = {
    "bins": bins,
    "weights": weights,
    "N_importance": N_importance,
    "det": det,
    "eps": eps,
}
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_hom Ran
ran; our contract draft was wrong, not the code
chenhsuanlin/bundle-adjusting-NeRF/camera.py
code served (permissive licence) · get_code("8ae29d1e7c9ed2f8")
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, 5) 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 to_hom takes a tensor X and concatenates ones along the last dimension
# X should be a tensor with shape (..., D) where D is some feature dimension
# The function will append a column of ones to make it homogeneous coordinates

X = torch.randn(2, 4)  # batch size 2, feature dimension 4

ARGS = {
    "X": X
}
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, 5) — shape (2, 5) 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
world2cam Ran
ran; our contract draft was wrong, not the code
chenhsuanlin/bundle-adjusting-NeRF/camera.py
code served (permissive licence) · get_code("7e76538e2f377f4d")
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)

class Pose:
    """
    A class of operations on camera poses (PyTorch tensors with shape [...,3,4])
    each [3,4] camera pose takes the form of [R|t]
    """

    def __call__(self, R=None, t=None):
        assert R is not None or t is not None
        if R is None:
            if not isinstance(t, torch.Tensor):
                t = torch.tensor(t)
            R = torch.eye(3, device=t.device).repeat(*t.shape[:-1], 1, 1)
        elif t is None:
            if not isinstance(R, torch.Tensor):
                R = torch.tensor(R)
            t = torch.zeros(R.shape[:-1], device=R.device)
        else:
            if not isinstance(R, torch.Tensor):
                R = torch.tensor(R)
            if not isinstance(t, torch.Tensor):
                t = torch.tensor(t)
        assert R.shape[:-1] == t.shape and R.shape[-2:] == (3, 3)
        R = R.float()
        t = t.float()
        pose = torch.cat([R, t[..., None]], dim=-1)
        assert pose.shape[-2:] == (3, 4)
        return pose

    def invert(self, pose, use_inverse=False):
        R, t = (pose[..., :3], pose[..., 3:])
        R_inv = R.inverse() if use_inverse else R.transpose(-1, -2)
        t_inv = (-R_inv @ t)[..., 0]
        pose_inv = self(R=R_inv, t=t_inv)
        return pose_inv

    def compose(self, pose_list):
        pose_new = pose_list[0]
        for pose in pose_list[1:]:
            pose_new = self.compose_pair(pose_new, pose)
        return pose_new

    def compose_pair(self, pose_a, pose_b):
        R_a, t_a = (pose_a[..., :3], pose_a[..., 3:])
        R_b, t_b = (pose_b[..., :3], pose_b[..., 3:])
        R_new = R_b @ R_a
        t_new = (R_b @ t_a + t_b)[..., 0]
        pose_new = self(R=R_new, t=t_new)
        return pose_new

def to_hom(X):
    X_hom = torch.cat([X, torch.ones_like(X[..., :1])], dim=-1)
    return X_hom

def world2cam(X, pose):
    X_hom = to_hom(X)
    return X_hom @ pose.transpose(-1, -2)

pose_obj = Pose()
R = torch.eye(3, dtype=torch.float32).unsqueeze(0).repeat(2, 1, 1)
t = torch.zeros(2, 3, dtype=torch.float32)
pose_tensor = pose_obj(R=R, t=t)
X = torch.randn(2, 4, 3, dtype=torch.float32)

ARGS = {
    "X": X,
    "pose": pose_tensor,
}
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
PinholeModelRotNoiseLearning10kRayoRaydDistortion Not yet run
unverified (harvested, no recorded run)
postech-cvlab/scnerf/model/camera_model.py
code served (permissive licence) · get_code("60ca8c9c18693dbc")
How it ran

no invocation recorded.

cam2img Not yet run
unverified (harvested, no recorded run)
chenhsuanlin/bundle-adjusting-NeRF/camera.py
code served (permissive licence) · get_code("54e93b2a1fc19f41")
How it ran

no invocation recorded.

color_border Not yet run
unverified (harvested, no recorded run)
chenhsuanlin/bundle-adjusting-NeRF/util_vis.py
code served (permissive licence) · get_code("ec862b3024c7ea71")
How it ran

no invocation recorded.

create_dataloader Not yet run
unverified (harvested, no recorded run)
MQ66/gnerf/dataset/dataloader.py
code served (permissive licence) · get_code("7c0f83be3b1230bb")
How it ran

no invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
MQ66/gnerf/dataset/dataloader.py
code served (permissive licence) · get_code("3824193054538982")
How it ran

no invocation recorded.

get_heatmap Not yet run
unverified (harvested, no recorded run)
chenhsuanlin/bundle-adjusting-NeRF/util_vis.py
code served (permissive licence) · get_code("3dcfc350d47d5fc9")
How it ran

no invocation recorded.

inference Not yet run
unverified (harvested, no recorded run)
MQ66/gnerf/model/rendering.py
code served (permissive licence) · get_code("c5960ba148e94710")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 5 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
to_hom 4 other papers
1 dated earlier, 3 later
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
2304.12294 (2023-04)
Explicit Correspondence Matching for Generalizable Neural Radiance Fields
2306.04166 (2023-06)
BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitives
and 1 more not named here
cam2img 3 other papers
1 dated earlier, 2 later
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
2304.12294 (2023-04)
Explicit Correspondence Matching for Generalizable Neural Radiance Fields
aaai_27859 (2024 (year only))
Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields
load_options 3 other papers
1 dated earlier, 2 later
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
2304.12294 (2023-04)
Explicit Correspondence Matching for Generalizable Neural Radiance Fields
2312.04565 (2023-12)
MuRF: Multi-Baseline Radiance Fields
world2cam 3 other papers
1 dated earlier, 2 later
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
2304.12294 (2023-04)
Explicit Correspondence Matching for Generalizable Neural Radiance Fields
aaai_27859 (2024 (year only))
Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields
parse_arguments 2 other papers
1 dated earlier, 1 later
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
2312.04565 (2023-12)
MuRF: Multi-Baseline Radiance Fields
blue 1 other paper
1 dated earlier
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
get_heatmap 1 other paper
1 dated earlier
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
green 1 other paper
1 dated earlier
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
inference 1 other paper
1 dated earlier
2103.15606 (2021-03)
GNeRF: GAN-based Neural Radiance Field without Posed Camera
red 1 other paper
1 dated earlier
2010.10505 (2020-10)
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
sample_pdf 1 other paper
1 dated earlier
2103.15606 (2021-03)
GNeRF: GAN-based Neural Radiance Field without Posed Camera

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

Neural Radiance Fields (NeRF) [31] have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of realworld scenes. One limitation of NeRF, however, is its requirement of accurate camera poses to learn the scene representations. In this paper, we propose Bundle-Adjusting Neural Radiance Fields (BARF) for training NeRF from imperfect (or even unknown) camera poses -the joint problem of learning neural 3D representations and registering camera frames. We establish a theoretical connection to classical image alignment and show that coarse-to-fine registration is also applicable to NeRF. Furthermore, we show that naïvely applying positional encoding in NeRF has a negative impact on registration with a synthesis-based objective. Experiments on synthetic and real-world data show that BARF can effectively optimize the neural scene representations and resolve large camera pose misalignment at the same time. This enables view synthesis and localization of video sequences from unknown camera poses, opening up new avenues for visual localization systems (e.g. SLAM) and potential applications for dense 3D mapping and reconstruction.

For agents

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

get_harvested_code_for_paper("2104.06405")
get_code_for_paper("2104.06405")
have("2104.06405")

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

curl https://syntology.ai/api/ran/2104.06405.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.06405.svg)](https://syntology.ai/paper/2104.06405)

Connect an agent — have() is free.