SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.00788 · CVPR · 2023

Open-Vocabulary Point-Cloud Object Detection without 3D Annotation

Kurt Keutzer, Masayoshi Tomizuka, Shanghang Zhang, Chenfeng Xu, Yuheng Lu, Xiaodong Xie, Wei Xiaobao

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 (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2304.00788.json · badge: /api/ran/2304.00788.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
lyhdet/OV-3DET community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
DTCC_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lyhdet/OV-3DET/dtcc_loss.py
code served (permissive licence) · get_code("4d62fde816630f80")
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) 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
from torch import nn

torch.manual_seed(0)

# Construct a tensor for objs
# Each row: [feature_dims..., class_label, score]
# Let's use feature_dim=4, so each row has 6 elements (4 features + 1 class + 1 score)
feature_dim = 4
num_objects = 3

# Create objs tensor with shape (num_objects, feature_dim + 2)
# Columns: [feat0, feat1, feat2, feat3, class_label, score]
objs = torch.randn(num_objects, feature_dim + 2, dtype=torch.float32)

# Set class labels (last column - 1) to have some variation
objs[:, -2] = torch.tensor([0.0, 0.0, 1.0])  # Two objects of class 0, one of class 1

# Set scores (last column)
objs[:, -1] = torch.tensor([0.9, 0.8, 0.7])

# Set temperature parameter
temperature = 0.1

ARGS = {
    "objs": objs,
    "temperature": temperature,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
cal_sim Ran
ran, honoured the contract we drafted
lyhdet/OV-3DET/dtcc_loss.py
code served (permissive licence) · get_code("c5cf686f87e20400")
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
import torch.nn as nn

torch.manual_seed(0)

# Create two small tensors with distinct dimensions
# z_i: batch_size=2, embedding_dim=4
z_i = torch.randn(2, 4)

# z_j: batch_size=3, embedding_dim=4 (different batch size for distinctness)
z_j = torch.randn(3, 4)

# Temperature parameter for scaling
temperature = 0.07

ARGS = {
    "z_i": z_i,
    "z_j": z_j,
    "temperature": temperature,
}
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

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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 1 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
cal_sim
brick of this paper's assembly: helper
1 other paper
1 later
2407.08931 (2024-07)
Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection

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

The goal of open-vocabulary detection is to identify novel objects based on arbitrary textual descriptions. In this paper, we address open-vocabulary 3D point-cloud detection by a dividing-and-conquering strategy, which involves: 1) developing a point-cloud detector that can learn a general representation for localizing various objects, and 2) connecting textual and point-cloud representations to enable the detector to classify novel object categories based on text prompting. Specifically, we resort to rich image pre-trained models, by which the point-cloud detector learns localizing objects under the supervision of predicted 2D bounding boxes from 2D pre-trained detectors. Moreover, we propose a novel de-biased triplet cross-modal contrastive learning to connect the modalities of image, point-cloud and text, thereby enabling the point-cloud detector to benefit from vision-language pre-trained models, i.e., CLIP. The novel use of image and vision-language pretrained models for point-cloud detectors allows for openvocabulary 3D object detection without the need for 3D annotations. Experiments demonstrate that the proposed method improves at least 3.03 points and 7.47 points over a wide range of baselines on the ScanNet and SUN RGB-D datasets, respectively. Furthermore, we provide a comprehensive analysis to explain why our approach works. Code is available at https://github.com/lyhdet/OV-3DET

For agents

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

get_harvested_code_for_paper("2304.00788")
get_code_for_paper("2304.00788")
have("2304.00788")

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

curl https://syntology.ai/api/ran/2304.00788.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.00788.svg)](https://syntology.ai/paper/2304.00788)

Connect an agent — have() is free.