SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.01100 · CVPR · 2021

Categorical Depth Distribution Network for Monocular 3D Object Detection

Ali Harakeh, Steven Waslander, Cody Reading, Julia Chae

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2103.01100.json · badge: /api/ran/2103.01100.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
TRAILab/CaDDN marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
CaDDN Ran
ran on a synthesized input · constructed an object; no result was computed
TRAILab/CaDDN/pcdet/models/detectors/caddn.py
code served (permissive licence) · get_code("4c532f0ca5d8df1a")
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, CaDDN: 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 SimpleDataset:
    def __init__(self):
        self.class_names = ['car', 'pedestrian', 'cyclist']
        self.point_feature_encoder = SimplePointFeatureEncoder()
        self.grid_size = [100, 100, 100]
        self.point_cloud_range = [0, 0, 0, 100, 100, 100]
        self.voxel_size = [0.1, 0.1, 0.1]
        self.depth_downsample_factor = 1

class SimplePointFeatureEncoder:
    def __init__(self):
        self.num_point_features = 4

class SimpleConfig:
    def __init__(self):
        self.VFE = None
        self.FFE = None
        self.F2V = None
        self.BACKBONE_3D = None
        self.MAP_TO_BEV = None
        self.PFE = None
        self.BACKBONE_2D = None
        self.DENSE_HEAD = None
        self.POINT_HEAD = None
        self.ROI_HEAD = None
    
    def get(self, key, default=None):
        return getattr(self, key, default)

ARGS = {
    'model_cfg': SimpleConfig(),
    'num_class': 3,
    'dataset': SimpleDataset()
}
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 CaDDN — 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 CaDDN 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
Detector3DTemplate Ran
ran on a synthesized input · constructed an object; no result was computed
TRAILab/CaDDN/pcdet/models/detectors/caddn.py
code served (permissive licence) · get_code("4c955a83c7e839c1")
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, Detector3DTemplate: 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 MockPointFeatureEncoder:
    def __init__(self):
        self.num_point_features = 4

class MockDataset:
    def __init__(self):
        self.class_names = ['car', 'pedestrian', 'cyclist']
        self.point_feature_encoder = MockPointFeatureEncoder()
        self.grid_size = [100, 100, 10]
        self.point_cloud_range = [0, 0, 0, 100, 100, 10]
        self.voxel_size = [1.0, 1.0, 1.0]
        self.depth_downsample_factor = 2

class MockConfig:
    def __init__(self):
        self.VFE = None
        self.FFE = None
        self.F2V = None
        self.BACKBONE_3D = None
        self.MAP_TO_BEV = None
        self.BACKBONE_2D = None
        self.PFE = None
        self.DENSE_HEAD = None
        self.POINT_HEAD = None
        self.ROI_HEAD = None
    
    def get(self, key, default=None):
        return getattr(self, key, default)

model_cfg = MockConfig()
num_class = 3
dataset = MockDataset()

ARGS = {
    'model_cfg': model_cfg,
    'num_class': num_class,
    'dataset': dataset
}
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 Detector3DTemplate — 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 Detector3DTemplate 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Monocular 3D object detection is a key problem for autonomous vehicles, as it provides a solution with simple configuration compared to typical multi-sensor systems. The main challenge in monocular 3D detection lies in accurately predicting object depth, which must be inferred from object and scene cues due to the lack of direct range measurement. Many methods attempt to directly estimate depth to assist in 3D detection, but show limited performance as a result of depth inaccuracy. Our proposed solution, Categorical Depth Distribution Network (CaDDN), uses a predicted categorical depth distribution for each pixel to project rich contextual feature information to the appropriate depth interval in 3D space. We then use the computationally efficient bird's-eye-view projection and single-stage detector to produce the final output detections. We design CaDDN as a fully differentiable end-to-end approach for joint depth estimation and object detection. We validate our approach on the KITTI 3D object detection benchmark, where we rank 1 st among published monocular methods. We also provide the first monocular 3D detection results on the newly released Waymo Open Dataset. We provide a code release for CaDDN which is made available.

For agents

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

get_harvested_code_for_paper("2103.01100")
get_code_for_paper("2103.01100")
have("2103.01100")

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

curl https://syntology.ai/api/ran/2103.01100.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.01100.svg)](https://syntology.ai/paper/2103.01100)

Connect an agent — have() is free.