SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.10528 · ICCV · 2021

ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation

Dani Lischinski, Yangyan Li, Jinming Cao, Hanchao Leng, Danny Cohen-Or, Changhe Tu

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 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/2108.10528.json · badge: /api/ran/2108.10528.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
hanchaoleng/shapeconv canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
get_names Ran
ran on a synthesized input
hanchaoleng/shapeconv/data_preparation/gen_sid.py
code served (permissive licence) · get_code("77c65c7d1af59cce")
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 os
import tempfile
import shutil

# Create a temporary directory structure that matches what get_names expects
temp_dir = tempfile.mkdtemp()
area_name = "test_area"
area_dir = os.path.join(temp_dir, area_name, "data", "rgb")
os.makedirs(area_dir, exist_ok=True)

# Create some test image files with appropriate naming pattern
test_files = [
    "image_001_0.png",
    "image_002_0.jpg",
    "photo_003_0.png",
]

for filename in test_files:
    filepath = os.path.join(area_dir, filename)
    with open(filepath, 'w') as f:
        f.write("")  # Create empty file

ARGS = {
    "dir_in": temp_dir,
    "area": area_name,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
read_label_map Ran
ran on a synthesized input
hanchaoleng/shapeconv/data_preparation/gen_nyu.py
code served (permissive licence) · get_code("250eeac5dd1759bc")
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
import scipy.io as scio
import tempfile
import os

# Create a temporary .mat file with the required structure
temp_dir = tempfile.mkdtemp()
path_map = os.path.join(temp_dir, "test_map.mat")

# Create a mock .mat file with classMapping13 structure
# The function expects: f_map['classMapping13'][0][0][0][0] to be an array
classMapping13_data = np.array([[[[np.array([1, 2, 3, 4, 5])]]]])
scio.savemat(path_map, {'classMapping13': classMapping13_data})

ARGS = {
    'path_map': path_map
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
save_list Ran
ran on a synthesized input
hanchaoleng/shapeconv/data_preparation/gen_sid.py
code served (permissive licence) · get_code("d83873f97d8b3da7")
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 os
import tempfile
import shutil

# Create temporary directories for the test
temp_input_dir = tempfile.mkdtemp()
temp_output_dir = tempfile.mkdtemp()

# Create the directory structure that get_names expects
for area in ['area_1', 'area_2', 'area_3', 'area_4', 'area_6', 'area_5a', 'area_5b']:
    rgb_dir = os.path.join(temp_input_dir, area, 'data', 'rgb')
    os.makedirs(rgb_dir, exist_ok=True)
    
    # Create some dummy image files
    for i in range(2):
        filename = f'image_{i}_rgb.png'
        filepath = os.path.join(rgb_dir, filename)
        with open(filepath, 'w') as f:
            f.write('')

ARGS = {
    'dir_in': temp_input_dir,
    'dir_out': temp_output_dir,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
get_nyu_cam_mats Not yet run
unverified (harvested, no recorded run)
hanchaoleng/shapeconv/data_preparation/gen_nyu.py
code served (permissive licence) · get_code("b046cfe2bfad70e5")
How it ran

no invocation recorded.

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, 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 4 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

RGB-D semantic segmentation has attracted increasing attention over the past few years. Existing methods mostly employ homogeneous convolution operators to consume the RGB and depth features, ignoring their intrinsic differences. In fact, the RGB values capture the photometric appearance properties in the projected image space, while the depth feature encodes both the shape of a local geometry as well as the base (whereabout) of it in a larger context. Compared with the base, the shape probably is more inherent and has a stronger connection to the semantics, and thus is more critical for segmentation accuracy. Inspired by this observation, we introduce a Shape-aware Convolutional layer (ShapeConv) for processing the depth feature, where the depth feature is firstly decomposed into a shape-component and a base-component, next two learnable weights are introduced to cooperate with them independently, and finally a convolution is applied on the re-weighted combination of these two components. ShapeConv is model-agnostic and can be easily integrated into most CNNs to replace vanilla convolutional layers for semantic segmentation. Extensive experiments on three challenging indoor RGB-D semantic segmentation benchmarks, i.e., NYU-Dv2(-13,-40), SUN RGB-D, and SID, demonstrate the effectiveness of our ShapeConv when employing it over five popular architectures. Moreover, the performance of CNNs with ShapeConv is boosted without introducing any computation and memory increase in the inference phase. The reason is that the learnt weights for balancing the importance between the shape and base components in ShapeConv become constants in the inference phase, and thus can be fused into the following convolution, resulting in a network that is identical to one with vanilla convolutional layers.

For agents

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

get_harvested_code_for_paper("2108.10528")
get_code_for_paper("2108.10528")
have("2108.10528")

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

curl https://syntology.ai/api/ran/2108.10528.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.10528.svg)](https://syntology.ai/paper/2108.10528)

Connect an agent — have() is free.