SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.08280 · 2024

WayveScenes101: A Dataset and Benchmark for Novel View Synthesis in Autonomous Driving

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 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/2407.08280.json · badge: /api/ran/2407.08280.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
wayveai/wayve_scenes canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
as_matrix Ran
ran, honoured the contract we drafted
wayveai/wayve_scenes/src/wayve_scenes/utils/intrmat.py
code served (permissive licence) · get_code("566fffd464233c81")
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, 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
from torch.utils.data import default_convert

torch.manual_seed(0)

# The function expects:
# - focal_lengths: a tensor of shape (batch, 2) or (2,) containing focal lengths
# - principal_points: a tensor of shape (batch, 2) or (2,) containing principal points (cx, cy)

# Create sample focal_lengths tensor - batch of 2, with 2 values per batch
focal_lengths = torch.tensor([[500.0, 510.0], [520.0, 530.0]])

# Create sample principal_points tensor - batch of 2, with 2 values per batch
principal_points = torch.tensor([[320.0, 240.0], [325.0, 245.0]])

ARGS = {
    "focal_lengths": focal_lengths,
    "principal_points": principal_points,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, 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, 3) — shape (2, 3, 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
check_valid_image Ran
ran, violated the contract we drafted
wayveai/wayve_scenes/src/wayve_scenes/evaluation.py
code served (permissive licence) · get_code("47bc01a937dab96d")
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 bool, 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 cv2
import tempfile
import os
import numpy as np

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

# Create a simple valid image using numpy and cv2
image_array = np.zeros((100, 100, 3), dtype=np.uint8)
image_array[:, :] = [255, 0, 0]  # Red image
cv2.imwrite(temp_image_path, image_array)

ARGS = {
    "path": temp_image_path
}
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 bool, 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
compute_psnr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wayveai/wayve_scenes/src/wayve_scenes/utils/metrics.py
code served (permissive licence) · get_code("af2f8d3d5e9992b2")
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 numpy as np

torch.manual_seed(0)

# Create small tensors: batch of 2 images with spatial dims 4x4 and 3 channels
pred = torch.rand(2, 4, 4, 3, dtype=torch.float32)
target = torch.rand(2, 4, 4, 3, dtype=torch.float32)

# Create a boolean mask with spatial shape matching pred (excluding channel dimension)
mask = torch.rand(2, 4, 4) > 0.5

ARGS = {
    'pred': pred,
    'target': target,
    'mask': mask,
    'normalise': False,
    'do_filtering': False,
}
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 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_focal_lengths Ran
ran, honoured the contract we drafted
wayveai/wayve_scenes/src/wayve_scenes/utils/intrmat.py
code served (permissive licence) · get_code("d1dde88549123fce")
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 (1, 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
import numpy as np

torch.manual_seed(0)

# Create a 3x3 intrinsics matrix (camera intrinsics)
# Standard format: [[fx, 0, cx], [0, fy, cy], [0, 0, 1]]
intrinsics_2d = torch.tensor([
    [500.0, 0.0, 320.0],
    [0.0, 500.0, 240.0],
    [0.0, 0.0, 1.0]
], dtype=torch.float32)

ARGS = {
    "intrinsics": intrinsics_2d
}
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 (1, 2) — shape (1, 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_principal_point Ran
ran, honoured the contract we drafted
wayveai/wayve_scenes/src/wayve_scenes/utils/intrmat.py
code served (permissive licence) · get_code("c9b0ece681ab90a2")
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, 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
import numpy as np

torch.manual_seed(0)

# Create a small intrinsics matrix
# Shape: (2, 3, 3) - batch of 2, 3x3 intrinsic matrices
# Intrinsics typically have focal length at [0,0] and [1,1], principal point at [0,2] and [1,2]
intrinsics_tensor = torch.tensor([
    [[500.0, 0.0, 320.0],
     [0.0, 500.0, 240.0],
     [0.0, 0.0, 1.0]],
    [[600.0, 0.0, 640.0],
     [0.0, 600.0, 480.0],
     [0.0, 0.0, 1.0]]
])

ARGS = {
    "intrinsics": intrinsics_tensor
}
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 (2, 2) — shape (2, 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
opencv_point_to_wayve_point Ran
ran; our contract draft was wrong, not the code
wayveai/wayve_scenes/src/wayve_scenes/utils/poses.py
code served (permissive licence) · get_code("282b42c0b3d3e32b")
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)

# Create a small tensor with shape (2, 3) representing 2 points in OpenCV format
# OpenCV format typically has (x, y, z) or similar coordinate ordering
points_opencv = torch.randn(2, 3)

ARGS = {
    "points_opencv": points_opencv
}
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
get_fid_metric Not yet run
unverified (harvested, no recorded run)
wayveai/wayve_scenes/src/wayve_scenes/utils/metrics.py
code served (permissive licence) · get_code("a2c117d68ebf46fc")
How it ran

no invocation recorded.

get_metrics Not yet run
unverified (harvested, no recorded run)
wayveai/wayve_scenes/src/wayve_scenes/utils/metrics.py
code served (permissive licence) · get_code("f43b4b442a26ff4d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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 WayveScenes101, a dataset designed to help the community advance the state of the art in novel view synthesis that focuses on challenging driving scenes containing many dynamic and deformable elements with changing geometry and texture. The dataset comprises 101 driving scenes across a wide range of environmental conditions and driving scenarios. The dataset is designed for benchmarking reconstructions on in-the-wild driving scenes, with many inherent challenges for scene reconstruction methods including image glare, rapid exposure changes, and highly dynamic scenes with significant occlusion. Along with the raw images, we include COLMAP-derived camera poses in standard data formats. We propose an evaluation protocol for evaluating models on held-out camera views that are off-axis from the training views, specifically testing the generalisation capabilities of methods. Finally, we provide detailed metadata for all scenes, including weather, time of day, and traffic conditions, to allow for a detailed model performance breakdown across scene characteristics. Dataset and code are available at https://github.com/wayveai/wayve_scenes.

For agents

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

get_harvested_code_for_paper("2407.08280")
get_code_for_paper("2407.08280")
have("2407.08280")

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

curl https://syntology.ai/api/ran/2407.08280.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.08280.svg)](https://syntology.ai/paper/2407.08280)

Connect an agent — have() is free.