SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.02550 · 2019

ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation

arXiv · PDF · Open in the Atlas

Code that ran

3 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 1 has no contract verdict; 2 failures of our instrument; 5 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/1910.02550.json · badge: /api/ran/1910.02550.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
Shreeyak/cleargrasp canonical (classifier label)
classifier basis: census
3 ran · 5 no recorded run
FunctionStatusWhere it lives
blend_2_images Ran
ran on a synthesized input
Shreeyak/cleargrasp/dataset_capture_gui/capture_image.py
code served (permissive licence) · get_code("ff26fc2e0556ca72")
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 ndarray, ndim 3, dtype family int, shape (4, 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 numpy as np
import cv2

# Create two small RGB images with distinct dimensions
img1 = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
img2 = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

# Define blend weights that sum to 1.0 for 50% transparency each
p1 = 0.5
p2 = 0.5

ARGS = {
    "img1": img1,
    "img2": img2,
    "p1": p1,
    "p2": p2,
}
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 ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 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
depth2rgb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Shreeyak/cleargrasp/api/utils.py
code served (permissive licence) · get_code("bda7db167fbb3824")
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 ndarray, ndim 3, dtype family int, shape (4, 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 numpy as np
import cv2

# Create a small depth image (H=4, W=3) with float32 dtype
# Values represent depth in meters
np.random.seed(0)
depth_img = np.random.uniform(0.1, 1.5, size=(4, 3)).astype(np.float32)

# Ensure some pixels have zero depth (holes)
depth_img[0, 0] = 0.0

ARGS = {
    "depth_img": depth_img,
    "min_depth": 0.0,
    "max_depth": 1.5,
    "color_mode": cv2.COLORMAP_JET,
    "reverse_scale": False,
    "dynamic_scaling": False,
}
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 ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 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
scale_depth Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Shreeyak/cleargrasp/api/utils.py
code served (permissive licence) · get_code("c926f1221e84d21d")
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 ndarray, ndim 2, dtype family int, shape (4, 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 numpy as np

# Create a small depth image in float32 format
# Depth values in meters (typical range 0-10 meters for depth cameras)
depth_image = np.random.uniform(0, 5, size=(4, 3)).astype(np.float32)

ARGS = {
    "depth_image": depth_image,
}
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 ndarray, ndim 2, dtype family int, shape (4, 3) — shape (4, 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
build_aspp Not yet run
unverified (harvested, no recorded run)
Shreeyak/cleargrasp/api/modeling/aspp.py
code served (permissive licence) · get_code("02f07d7390433817")
How it ran

no invocation recorded.

build_decoder Not yet run
unverified (harvested, no recorded run)
Shreeyak/cleargrasp/api/modeling/decoder.py
code served (permissive licence) · get_code("fca9cc83c0d4bb38")
How it ran

no invocation recorded.

build_decoder Not yet run
unverified (harvested, no recorded run)
Shreeyak/cleargrasp/api/modeling/decoder_masks.py
code served (permissive licence) · get_code("3a0df7487d037785")
How it ran

no invocation recorded.

get_release_scans Not yet run
unverified (harvested, no recorded run)
Shreeyak/cleargrasp/z-ignore-scripts-helper/download-scannet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Wang-pengfei/GGSD, is pointer only (licence: NONE) · get_code("5905d8e45b03578e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Wang-pengfei/GGSD, 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. No invocation recorded.

run_bash_cmd Not yet run
unverified (harvested, no recorded run)
Shreeyak/cleargrasp/z-ignore-scripts-helper/extract_scannet_sens_file.py
code served (permissive licence) · get_code("8fa4a903aa57678d")
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 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 5 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
build_aspp 6 other papers
1 dated earlier, 5 later
1802.02611 (2018-02)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
2010.06349 (2020-10)
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration
2104.06394 (2021-04)
All you need are a few pixels: semantic segmentation with PixelPick
and 3 more not named here
build_decoder 2 other papers
1 dated earlier, 1 later
1802.02611 (2018-02)
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
2108.00384 (2021-08)
Edge-competing Pathological Liver Vessel Segmentation with Limited Labels
get_release_scans 2 other papers
2 later
2211.15654 (2022-11)
OpenScene: 3D Scene Understanding with Open Vocabularies
2407.13362 (2024-07)
Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation
depth2rgb 1 other paper
1 later
2309.13039 (2023-09)
NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields
scale_depth 1 other paper
1 later
2309.13039 (2023-09)
NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields

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 a common part of everyday life, yet they possess unique visual properties that make them incredibly difficult for standard 3D sensors to produce accurate depth estimates for. In many cases, they often appear as noisy or distorted approximations of the surfaces that lie behind them. To address these challenges, we present ClearGrasp -- a deep learning approach for estimating accurate 3D geometry of transparent objects from a single RGB-D image for robotic manipulation. Given a single RGB-D image of transparent objects, ClearGrasp uses deep convolutional networks to infer surface normals, masks of transparent surfaces, and occlusion boundaries. It then uses these outputs to refine the initial depth estimates for all transparent surfaces in the scene. To train and test ClearGrasp, we construct a large-scale synthetic dataset of over 50,000 RGB-D images, as well as a real-world test benchmark with 286 RGB-D images of transparent objects and their ground truth geometries. The experiments demonstrate that ClearGrasp is substantially better than monocular depth estimation baselines and is capable of generalizing to real-world images and novel objects. We also demonstrate that ClearGrasp can be applied out-of-the-box to improve grasping algorithms' performance on transparent objects. Code, data, and benchmarks will be released. Supplementary materials available on the project website: https://sites.google.com/view/cleargrasp

For agents

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

get_harvested_code_for_paper("1910.02550")
get_code_for_paper("1910.02550")
have("1910.02550")

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

curl https://syntology.ai/api/ran/1910.02550.json

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

[![Syntology run record](https://syntology.ai/api/ran/1910.02550.svg)](https://syntology.ai/paper/1910.02550)

Connect an agent — have() is free.