SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.16235 · CVPR · 2023

Spatiotemporal Self-supervised Learning for Point Clouds in the Wild

Tong Zhang, Mathieu Salzmann, Sabine Süsstrunk, Wei Ke, Yanhao Wu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 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/2303.16235.json · badge: /api/ran/2303.16235.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
YanhaoWu/STSSL community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Byol_Pix Ran
ran on a synthesized input · constructed an object; no result was computed
YanhaoWu/STSSL/models/byol_pix.py
code served (permissive licence) · get_code("61bc781f7014aac0")
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 an instance of its own class, Byol_Pix: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Minimal mock for args
class Args:
    def __init__(self):
        self.use_intensity = False
        self.sparse_model = 'SparseResNet14'
        self.feature_size = 128

# Minimal model class that mimics sparse model behavior
class MockSparseModel(nn.Module):
    def __init__(self, in_channels=3, out_channels=512):
        super().__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.conv = nn.Conv3d(in_channels, out_channels, kernel_size=3, padding=1)
    
    def forward(self, x):
        # Mock sparse tensor-like output with C (coordinates) and F (features)
        class MockOutput:
            def __init__(self):
                self.C = torch.randint(0, 2, (8, 4))
                self.F = torch.randn(8, 512)
        return MockOutput()

# Minimal projection head for pixel-level
class MockProjectionHeadPix(nn.Module):
    def __init__(self, in_channels=512, out_channels=128, batch_nor=True, pix_level=False):
        super().__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.pix_level = pix_level
        self.fc = nn.Linear(in_channels, out_channels)
    
    def forward(self, x, pix_deal=True):
        if isinstance(x, list):
            return torch.stack([self.fc(item) for item in x])
        return self.fc(x.F if hasattr(x, 'F') else x)

# Minimal projection head
class MockProjectionHead(nn.Module):
    def __init__(self, in_channels=512, out_channels=128, batch_nor=True):
        super().__init__()
        self.fc = nn.Linear(in_channels, out_channels)
    
    def forward(self, x):
        if isinstance(x, list):
            return torch.stack([self.fc(item) for item in x])
        return self.fc(x.F if hasattr(x, 'F') else x)

# Minimal predictor
class MockPredictor(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(128, 128)
    
    def forward(self, x):
        return self.fc(x)

# Build arguments dictionary
ARGS = {
    'model': MockSparseModel,
    'model_preject': MockProjectionHead,
    'model_preject_pix': MockProjectionHeadPix,
    'mode_predict': MockPredictor,
    'dtype': torch.float32,
    'args': Args(),
    'K': 65536,
    'm': 0.999,
    'T': 0.1,
}
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 Byol_Pix — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Byol_Pix 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 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.

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

Self-supervised learning (SSL) has the potential to benefit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, existing methods employ contrastive learning strategies and define positive pairs by performing various augmentation of point clusters in a single frame. As such, these methods do not exploit the temporal nature of LiDAR data. In this paper, we introduce an SSL strategy that leverages positive pairs in both the spatial and temporal domain. To this end, we design (i) a point-to-cluster learning strategy that aggregates spatial information to distinguish objects; and (ii) a cluster-to-cluster learning strategy based on unsupervised object tracking that exploits temporal correspondences. We demonstrate the benefits of our approach via extensive experiments performed by self-supervised training on two large-scale LiDAR datasets and transferring the resulting models to other point cloud segmentation benchmarks. Our results evidence that our method outperforms the state-of-the-art point cloud SSL methods. 1

For agents

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

get_harvested_code_for_paper("2303.16235")
get_code_for_paper("2303.16235")
have("2303.16235")

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

curl https://syntology.ai/api/ran/2303.16235.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.16235.svg)](https://syntology.ai/paper/2303.16235)

Connect an agent — have() is free.