SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.04049 · 2024

Occupancy as Set of Points

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 2 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/2407.04049.json · badge: /api/ran/2407.04049.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
hustvl/osp canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
rotz Ran
ran, honoured the contract we drafted
hustvl/osp/utils/vis.py
code served (permissive licence) · get_code("a30067af1a83cdf2")
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 Tensor, ndim 2, dtype family float, shape (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 torch

torch.manual_seed(0)

# The function rotz takes a single parameter 't' which is used with:
# - torch.cos(t)
# - torch.sin(t)
# - torch.tensor() construction
# So 't' should be a scalar or tensor that can be passed to cos/sin

t = torch.tensor(0.5)

ARGS = {
    "t": t
}
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 Tensor, ndim 2, dtype family float, shape (3, 3) — shape (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
voxel2points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hustvl/osp/utils/vis.py
code served (permissive licence) · get_code("4124214e21574acc")
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 torch
import numpy as np

torch.manual_seed(0)

# Create a small voxel grid (3D tensor with class labels)
# Shape: (5, 4, 3) - small spatial dimensions
voxel_data = torch.randint(0, 20, (5, 4, 3), dtype=torch.int32)

# Set a few values to ignore labels to test masking
voxel_data[0, 0, 0] = 17
voxel_data[1, 1, 1] = 255

ARGS = {
    "voxel": voxel_data,
    "voxelSize": [0.2, 0.2, 0.2],
    "range": [-40.0, -40.0, -1.0, 40.0, 40.0, 5.4],
    "ignore_labels": [17, 255]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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
voxel_profile Ran
ran; our contract draft was wrong, not the code
hustvl/osp/utils/vis.py
code served (permissive licence) · get_code("bd1aa420eb46a2d4")
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 Tensor, ndim 2, dtype family float, shape (2, 7) 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 torch

torch.manual_seed(0)

# Construct voxel tensor: shape (2, 3) for batch of 2 voxels with 3 coordinates each
# The function expects voxel[:, :2] (x, y) and voxel[:, 2] (z)
voxel = torch.tensor([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0]
], dtype=torch.float32)

# voxel_size is a tuple/list of 3 elements: (width, length, height)
voxel_size = [0.5, 0.6, 0.7]

ARGS = {
    "voxel": voxel,
    "voxel_size": voxel_size
}
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 Tensor, ndim 2, dtype family float, shape (2, 7) — shape (2, 7) 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 0 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
rotz 1 other paper
1 dated earlier
2312.17118 (2023-12)
Fully Sparse 3D Occupancy Prediction
voxel2points 1 other paper
1 dated earlier
2312.17118 (2023-12)
Fully Sparse 3D Occupancy Prediction
voxel_profile 1 other paper
1 dated earlier
2312.17118 (2023-12)
Fully Sparse 3D Occupancy Prediction

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

In this paper, we explore a novel point representation for 3D occupancy prediction from multi-view images, which is named Occupancy as Set of Points. Existing camera-based methods tend to exploit dense volume-based representation to predict the occupancy of the whole scene, making it hard to focus on the special areas or areas out of the perception range. In comparison, we present the Points of Interest (PoIs) to represent the scene and propose OSP, a novel framework for point-based 3D occupancy prediction. Owing to the inherent flexibility of the point-based representation, OSP achieves strong performance compared with existing methods and excels in terms of training and inference adaptability. It extends beyond traditional perception boundaries and can be seamlessly integrated with volume-based methods to significantly enhance their effectiveness. Experiments on the Occ3D nuScenes occupancy benchmark show that OSP has strong performance and flexibility. Code and models are available at \url{https://github.com/hustvl/osp}.

For agents

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

get_harvested_code_for_paper("2407.04049")
get_code_for_paper("2407.04049")
have("2407.04049")

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

curl https://syntology.ai/api/ran/2407.04049.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.04049.svg)](https://syntology.ai/paper/2407.04049)

Connect an agent — have() is free.