SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.12754 · 2023

SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 0 have no contract verdict; 1 failure 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/2311.12754.json · badge: /api/ran/2311.12754.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
huang-yh/selfocc canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
read_occ3d_label Ran
ran; our contract draft was wrong, not the code
huang-yh/selfocc/eval_iou.py
code served (permissive licence) · get_code("65bf7ce1f97b1843")
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) and returned NpzFile. 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
from unittest.mock import Mock, MagicMock
import tempfile
import os

torch.manual_seed(0)

# Create a temporary directory structure to simulate the occ3d data
temp_dir = tempfile.mkdtemp()
data_dir = os.path.join(temp_dir, 'data', 'occ3d', 'gts')
os.makedirs(data_dir, exist_ok=True)

# Create a mock scene and token structure
scene_name = 'test_scene'
token = 'test_token_12345'
scene_token = 'scene_token_67890'

# Create the directory for the label file
label_dir = os.path.join(data_dir, scene_name, token)
os.makedirs(label_dir, exist_ok=True)

# Create a mock label file with some dummy data
label_data = {
    'semantics': np.random.randint(0, 18, size=(256, 256, 32), dtype=np.uint8),
    'mask_lidar': np.random.randint(0, 2, size=(256, 256, 32), dtype=np.uint8),
    'mask_camera': np.random.randint(0, 2, size=(256, 256, 32), dtype=np.uint8),
}
label_file_path = os.path.join(label_dir, 'labels.npz')
np.savez(label_file_path, **label_data)

# Create mock nusc object with get method
nusc = Mock()

def mock_get(obj_type, token_val):
    if obj_type == 'sample':
        return {'scene_token': scene_token}
    elif obj_type == 'scene':
        return {'name': scene_name}
    return {}

nusc.get = mock_get

# Create metas dict with token
metas = {
    'token': token
}

# Change to temp directory so relative path works
original_cwd = os.getcwd()
os.chdir(temp_dir)

ARGS = {
    'metas': metas,
    'nusc': nusc,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type NpzFile — a NpzFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a NpzFile output the recorded ndim 1 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
read_openoccupancy_label Not yet run
unverified (harvested, no recorded run)
huang-yh/selfocc/eval_iou.py
code served (permissive licence) · get_code("33c66cfa516fa447")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

3D occupancy prediction is an important task for the robustness of vision-centric autonomous driving, which aims to predict whether each point is occupied in the surrounding 3D space. Existing methods usually require 3D occupancy labels to produce meaningful results. However, it is very laborious to annotate the occupancy status of each voxel. In this paper, we propose SelfOcc to explore a self-supervised way to learn 3D occupancy using only video sequences. We first transform the images into the 3D space (e.g., bird's eye view) to obtain 3D representation of the scene. We directly impose constraints on the 3D representations by treating them as signed distance fields. We can then render 2D images of previous and future frames as self-supervision signals to learn the 3D representations. We propose an MVS-embedded strategy to directly optimize the SDF-induced weights with multiple depth proposals. Our SelfOcc outperforms the previous best method SceneRF by 58.7% using a single frame as input on SemanticKITTI and is the first self-supervised work that produces reasonable 3D occupancy for surround cameras on nuScenes. SelfOcc produces high-quality depth and achieves state-of-the-art results on novel depth synthesis, monocular depth estimation, and surround-view depth estimation on the SemanticKITTI, KITTI-2015, and nuScenes, respectively. Code: https://github.com/huang-yh/SelfOcc.

For agents

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

get_harvested_code_for_paper("2311.12754")
get_code_for_paper("2311.12754")
have("2311.12754")

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

curl https://syntology.ai/api/ran/2311.12754.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.12754.svg)](https://syntology.ai/paper/2311.12754)

Connect an agent — have() is free.