SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03890 · ECCV · 2022

ClearPose: Large-scale Transparent Object Dataset and Benchmark

Huijie Zhang, Xiaotong Chen, Zeren Yu, Anthony Opipari, Chadwicke Jenkins

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 3 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/2203.03890.json · badge: /api/ran/2203.03890.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
opipari/ClearPose canonical (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_aspect_ratios Ran
ran on a synthesized input
opipari/ClearPose/clearpose/xu_6dof/networks/references/detection/group_by_aspect_ratio.py
code served (permissive licence) · get_code("c80742139eb6e728")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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.utils.data
import torchvision
from PIL import Image
import io

torch.manual_seed(0)

# Create a minimal custom dataset with get_height_and_width method
class CustomDataset(torch.utils.data.Dataset):
    def __init__(self, size=2):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        # Return a tensor image and a dummy label
        img = torch.randn(3, 32, 48)  # 3 channels, height=32, width=48
        label = 0
        return img, label
    
    def get_height_and_width(self, idx):
        return 32, 48

# Create instance
dataset = CustomDataset(size=2)

ARGS = {
    "dataset": dataset,
    "indices": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
convert_to_xywh Ran
ran, honoured the contract we drafted
opipari/ClearPose/clearpose/xu_6dof/networks/references/detection/coco_eval.py
pointer only (licence: MIT); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("f31a58bf6457ced5")
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 yuhangzang/contextdet, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

create_aspect_ratio_groups Ran
ran on a synthesized input
opipari/ClearPose/clearpose/xu_6dof/networks/references/detection/group_by_aspect_ratio.py
code served (permissive licence) · get_code("7cea05639abe6cd9")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
from torch.utils.data import Dataset

torch.manual_seed(0)

class SimpleDataset(Dataset):
    """Minimal dataset that returns image and label"""
    def __init__(self, num_samples=5):
        self.num_samples = num_samples
        # Store simple image tensors of varying aspect ratios
        self.images = [
            torch.randn(3, 4, 6),  # aspect ratio 6/4 = 1.5
            torch.randn(3, 5, 10), # aspect ratio 10/5 = 2.0
            torch.randn(3, 8, 4),  # aspect ratio 4/8 = 0.5
            torch.randn(3, 6, 9),  # aspect ratio 9/6 = 1.5
            torch.randn(3, 4, 8),  # aspect ratio 8/4 = 2.0
        ]
    
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        img = self.images[idx]
        label = torch.tensor(idx)
        return img, label

dataset = SimpleDataset(num_samples=5)

ARGS = {
    "dataset": dataset,
    "k": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
evaluate Ran
ran on a synthesized input
opipari/ClearPose/clearpose/xu_6dof/networks/references/detection/coco_eval.py
code served (permissive licence) · get_code("c020cdba64094eae")
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 numpy as np

class MockParams:
    def __init__(self):
        self.imgIds = [1, 2, 3]
        self.areaRng = [[0, 10000], [10000, 100000]]

class MockImgs:
    def __init__(self):
        self.params = MockParams()
        # evalImgs needs to be reshaped to (len(areaRng), len(imgIds))
        # which is (2, 3) = 6 elements
        self.evalImgs = np.arange(6, dtype=np.float32)
    
    def evaluate(self):
        # This method is called but does nothing
        pass

imgs = MockImgs()

ARGS = {
    "imgs": imgs
}
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 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
convert_to_xywh 24 other papers
8 dated earlier, 15 later, 1 same year, order not determinable
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 21 more not named here
compute_aspect_ratios 1 other paper
1 dated earlier
2106.03427 (2021-06)
Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring

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

Transparent objects are ubiquitous in household settings and pose distinct challenges for visual sensing and perception systems. The optical properties of transparent objects leave conventional 3D sensors alone unreliable for object depth and pose estimation. These challenges are highlighted by the shortage of large-scale RGB-Depth datasets focusing on transparent objects in real-world settings. In this work, we contribute a large-scale real-world RGB-Depth transparent object dataset named ClearPose to serve as a benchmark dataset for segmentation, scene-level depth completion and object-centric pose estimation tasks. The ClearPose dataset contains over 350K labeled real-world RGB-Depth frames and 5M instance annotations covering 63 household objects. The dataset includes object categories commonly used in daily life under various lighting and occluding conditions as well as challenging test scenarios such as cases of occlusion by opaque or translucent objects, non-planar orientations, presence of liquids, etc. We benchmark several state-of-theart depth completion and object pose estimation deep neural networks on ClearPose. The dataset and benchmarking source code is available at https://github.com/opipari/ClearPose.

For agents

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

get_harvested_code_for_paper("2203.03890")
get_code_for_paper("2203.03890")
have("2203.03890")

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

curl https://syntology.ai/api/ran/2203.03890.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03890.svg)](https://syntology.ai/paper/2203.03890)

Connect an agent — have() is free.