SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.01068 · 2020

Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination

arXiv · PDF · Open in the Atlas

Code that ran

1 of 9 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; 0 failures of our instrument; 8 no recorded run), measured 2026-11-21; 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/2008.01068.json · badge: /api/ran/2008.01068.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
Microsoft/O-CNN canonical (classifier label)
classifier basis: census
1 ran · 8 no recorded run
FunctionStatusWhere it lives
get_input_signal Ran
ran on a synthesized input
Microsoft/O-CNN/tensorflow/script/network_completion.py
code served (permissive licence) · get_code("9771607aa9495cf5")
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 EagerTensor, ndim 4, 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 tensorflow as tf
import numpy as np

# Mock octree_property function since it's called in get_input_signal
def octree_property(octree, property_name, dtype, depth, channel):
    """Mock implementation that returns a tensor of appropriate shape"""
    # Return a tensor with shape that will be reshaped to [1, channel, -1, 1]
    # So we need total elements = channel * something
    # Let's return shape [channel * 8] which will reshape to [1, channel, 8, 1]
    return tf.random.normal([channel * 8], dtype=dtype)

# Create a minimal octree mock object
class MockOctree:
    """Minimal octree mock - the function only passes it to octree_property"""
    def __init__(self):
        self.data = {}

# Patch octree_property into the module namespace for the function
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'octree_property', octree_property)

# Define arguments
ARGS = {
    'octree': MockOctree(),
    'depth': 3,
    'channel': 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float — no output shape is stated: observe_signature.py could not observe it (fixture:KeyError)
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
branch Not yet run
unverified (harvested, no recorded run)
Microsoft/O-CNN/tensorflow/script/network_hrnet.py
code served (permissive licence) · get_code("33c8859edabefe8e")
How it ran

no invocation recorded.

branches Not yet run
unverified (harvested, no recorded run)
Microsoft/O-CNN/tensorflow/script/network_hrnet.py
code served (permissive licence) · get_code("f2dc23962695d2b5")
How it ran

no invocation recorded.

cls_network Not yet run
unverified (harvested, no recorded run)
Microsoft/O-CNN/tensorflow/script/network_cls.py
code served (permissive licence) · get_code("2d88271666e60392")
How it ran

no invocation recorded.

get_split_label Not yet run
unverified (harvested, no recorded run)
Microsoft/O-CNN/tensorflow/script/network_completion.py
code served (permissive licence) · get_code("26fdcaa081b14291")
How it ran

no invocation recorded.

make_autoencoder Not yet run
unverified (harvested, no recorded run)
Microsoft/O-CNN/tensorflow/script/network_ae.py
code served (permissive licence) · get_code("a118ef8b9502a8ce")
How it ran

no invocation recorded.

network_ocnn Not yet run
unverified (harvested, no recorded run)
Microsoft/O-CNN/tensorflow/script/network_cls.py
code served (permissive licence) · get_code("e38b3343da083701")
How it ran

no invocation recorded.

network_resnet Not yet run
unverified (harvested, no recorded run)
Microsoft/O-CNN/tensorflow/script/network_cls.py
code served (permissive licence) · get_code("37dc89159ef62b72")
How it ran

no invocation recorded.

trans_func Not yet run
unverified (harvested, no recorded run)
Microsoft/O-CNN/tensorflow/script/network_hrnet.py
code served (permissive licence) · get_code("4ea8008f161405ca")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various shape analysis tasks with competitive performance to supervised methods. In this paper, we propose an unsupervised method for learning a generic and efficient shape encoding network for different shape analysis tasks. The key idea of our method is to jointly encode and learn shape and point features from unlabeled 3D point clouds. For this purpose, we adapt HR-Net to octree-based convolutional neural networks for jointly encoding shape and point features with fused multiresolution subnetworks and design a simple-yet-efficient Multiresolution Instance Discrimination (MID) loss for jointly learning the shape and point features. Our network takes a 3D point cloud as input and output both shape and point features. After training, the network is concatenated with simple task-specific back-end layers and fine-tuned for different shape analysis tasks. We evaluate the efficacy and generality of our method and validate our network and loss design with a set of shape analysis tasks, including shape classification, semantic shape segmentation, as well as shape registration tasks. With simple back-ends, our network demonstrates the best performance among all unsupervised methods and achieves competitive performance to supervised methods, especially in tasks with a small labeled dataset. For fine-grained shape segmentation, our method even surpasses existing supervised methods by a large margin.

For agents

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

get_harvested_code_for_paper("2008.01068")
get_code_for_paper("2008.01068")
have("2008.01068")

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

curl https://syntology.ai/api/ran/2008.01068.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.01068.svg)](https://syntology.ai/paper/2008.01068)

Connect an agent — have() is free.