SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.07535 · CVPR · 2024

Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving

Xin Yang, Wei Yin, Shijie Wang, Kaixuan Wang, Xiaozhi Chen, Junda Cheng

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 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/2403.07535.json · badge: /api/ran/2403.07535.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
junda24/afnet canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_depth_expectation Ran
ran; our contract draft was wrong, not the code
junda24/afnet/networks/module.py
code served (permissive licence) · get_code("bf60c0386e0f9109")
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, 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)

# Analyzing the function:
# - p: tensor that gets multiplied with depth_values along dimension 1
# - depth_values: tensor that gets viewed and summed with p
# The function does: torch.sum(p * depth_values, 1)
# This suggests p has shape (batch, num_depths, height, width)
# and depth_values has shape (num_depths,)

batch_size = 2
num_depths = 4
height = 3
width = 5

# p: probability map, shape (batch, num_depths, height, width)
p = torch.rand(batch_size, num_depths, height, width)

# depth_values: depth values for each depth plane, shape (num_depths,)
depth_values = torch.linspace(0.5, 5.0, num_depths)

ARGS = {
    "p": p,
    "depth_values": depth_values,
}
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, 3, 5) — shape (2, 3, 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
compute_errors Ran
ran; our contract draft was wrong, not the code
junda24/afnet/hybrid_evaluate_depth.py
code served (permissive licence) · get_code("9474d17a32751f12")
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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create small ground truth and prediction depth maps
# Shape: (4, 3) for small tensors
gt = np.random.uniform(0.5, 10.0, size=(4, 3)).astype(np.float32)
pred = np.random.uniform(0.5, 10.0, size=(4, 3)).astype(np.float32)

# Ensure pred is not too far from gt to avoid numerical issues
pred = gt + np.random.uniform(-0.5, 0.5, size=(4, 3)).astype(np.float32)
pred = np.clip(pred, 0.1, None)  # Ensure positive values for log

# Parameters for the function
disable_median_scaling = False
min_depth = 0.1
max_depth = 80.0
interval = 0.1

ARGS = {
    'gt': gt,
    'pred': pred,
    'disable_median_scaling': disable_median_scaling,
    'min_depth': min_depth,
    'max_depth': max_depth,
    'interval': interval
}
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 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
compute_errors1 Ran
ran; our contract draft was wrong, not the code
junda24/afnet/hybrid_evaluate_depth.py
code served (permissive licence) · get_code("55e5351176f727b5")
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 numpy as np

# Create small ground truth and prediction depth maps
np.random.seed(0)
gt = np.random.uniform(0.5, 10.0, size=(4, 3)).astype(np.float32)
pred = np.random.uniform(0.5, 10.0, size=(4, 3)).astype(np.float32)

# Ensure pred and gt are positive and reasonable for depth estimation
gt = np.abs(gt) + 0.1
pred = np.abs(pred) + 0.1

ARGS = {
    'gt': gt,
    'pred': pred,
    'disable_median_scaling': False,
    'min_depth': 0.1,
    'max_depth': 100.0,
    'interval': 0.1,
}
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 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
compute_errors_perimage Ran
ran; our contract draft was wrong, not the code
junda24/afnet/hybrid_evaluate_depth.py
code served (permissive licence) · get_code("adacae53f5f26c8a")
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 numpy as np

# Create small depth maps for ground truth and prediction
# Shape: (4, 3) - small spatial dimensions
np.random.seed(0)
gt = np.random.uniform(0.5, 80.0, size=(4, 3)).astype(np.float32)
pred = np.random.uniform(0.5, 80.0, size=(4, 3)).astype(np.float32)

# Depth range parameters
min_depth = 0.1
max_depth = 100.0

ARGS = {
    'gt': gt,
    'pred': pred,
    'min_depth': min_depth,
    'max_depth': max_depth
}
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 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
convbn Ran
ran; our contract draft was wrong, not the code
junda24/afnet/networks/module.py
pointer only (licence: MIT); the stored copy get_code serves, from lijia7/sddr, is pointer only (licence: NONE) · get_code("4589ab426bdcfbb8")
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 lijia7/sddr, 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.

homo_warping Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
junda24/afnet/networks/module.py
code served (permissive licence) · get_code("13b987a70bd64ee2")
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 torch.nn as nn

torch.manual_seed(0)

# Define tensor dimensions
batch_size = 2
channels = 4
height_ref = 3
width_ref = 3
height_src = 5
width_src = 5
num_depth = 2

# src_fea: feature map from source image (batch, channels, height_src, width_src)
src_fea = torch.randn(batch_size, channels, height_src, width_src)

# T_ref2src: transformation matrix from reference to source (batch, 4, 4)
# Contains 3x3 rotation and 3x1 translation
T_ref2src = torch.eye(4).unsqueeze(0).repeat(batch_size, 1, 1)
T_ref2src[:, 0, 3] = 0.1  # small translation in x
T_ref2src[:, 1, 3] = 0.05  # small translation in y

# depth_values: depth values at reference view (batch, num_depth, height_ref, width_ref)
depth_values = torch.linspace(0.5, 5.0, num_depth).view(1, num_depth, 1, 1).repeat(batch_size, 1, height_ref, width_ref)

# inv_K: inverse of intrinsic camera matrix (batch, 4, 4)
# Standard camera intrinsics inverted
K = torch.tensor([
    [500.0, 0.0, width_src/2],
    [0.0, 500.0, height_src/2],
    [0.0, 0.0, 1.0]
], dtype=torch.float32)
K_inv = torch.inverse(K)
inv_K = torch.eye(4).unsqueeze(0).repeat(batch_size, 1, 1)
inv_K[:, :3, :3] = K_inv

ARGS = {
    "src_fea": src_fea,
    "T_ref2src": T_ref2src,
    "depth_values": depth_values,
    "inv_K": inv_K,
}
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 — 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
mobilenet_v2 Ran
ran; our contract draft was wrong, not the code
junda24/afnet/networks/mobilenet.py
code served (permissive licence) · get_code("90813520c84cd028")
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 MobileNetV2. 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)

ARGS = {
    'num_classes': 10,
    'width_mult': 1.0,
    'inverted_residual_setting': None,
    'round_nearest': 8,
    'block': None,
    'norm_layer': None,
}
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 MobileNetV2 — a MobileNetV2 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MobileNetV2 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
homo_warping_depth Not yet run
unverified (harvested, no recorded run)
junda24/afnet/generate_dynamic_mask.py
code served (permissive licence) · get_code("da8bd713137a0726")
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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 5 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
convbn 5 other papers
2 dated earlier, 2 later, 1 same year, order not determinable
2104.04314 (2021-04)
CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching
2312.09243 (2023-12)
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments
and 2 more not named here
mobilenet_v2 5 other papers
3 dated earlier, 2 later
2105.03245 (2021-05)
Adaptive Focus for Efficient Video Recognition
2211.16231 (2022-11)
Curriculum Temperature for Knowledge Distillation
2310.04918 (2023-10)
SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning
and 2 more not named here
compute_depth_expectation 1 other paper
1 dated earlier
2104.13325 (2021-04)
MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions

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

Figure 1. Visualization of reconstructed 3D point clouds of DDAD [12] scenes. We fuse the results of 10 frames (including the dynamic object cars) and zoom in on some details for visualization. It shows that our method can achieve high-quality results on both static and dynamic parts.

For agents

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

get_harvested_code_for_paper("2403.07535")
get_code_for_paper("2403.07535")
have("2403.07535")

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

curl https://syntology.ai/api/ran/2403.07535.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.07535.svg)](https://syntology.ai/paper/2403.07535)

Connect an agent — have() is free.