SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.09551 · ICCV · 2023

SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving

Jiwen Lu, Jie Zhou, Zheng Zhu, Wenzhao Zheng, Yi Wei, Linqing Zhao

arXiv · PDF · Open in the Atlas

Code that ran

18 of 24 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; 4 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 11 failures of our instrument; 6 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/2303.09551.json · badge: /api/ran/2303.09551.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
weiyithu/SurroundOcc canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
ganwanshui/simpleoccupancy community
Papers with Code archive
15 ran · 5 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
LaplaceDensity Ran
ran on a synthesized input
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("048f8b844c751fe1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_4x4 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("8fd8e2bb9940b788")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convbn_3d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("ea83495b07c4dc60")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cumprod_exclusive Ran
ran; our contract draft was wrong, not the code
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("06e6d02b8b324672")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

eye_4x4 Ran
ran, honoured the contract we drafted
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("7479150fe85cefe6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

geo_scal_loss Ran
ran on a synthesized input
weiyithu/SurroundOcc/projects/mmdet3d_plugin/surroundocc/loss/loss_utils.py
code served (permissive licence) · get_code("53c587a7165aa47b")
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 0, dtype family float, shape () 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small 5D tensor for predictions (batch, channels, depth, height, width)
# batch=2, channels=4 (for semantic classes), depth=3, height=3, width=3
pred = torch.randn(2, 4, 3, 3, 3)

# Create target tensor with shape (batch, depth, height, width)
# Values should be class indices (0-3) or 255 (ignore index)
ssc_target = torch.randint(0, 4, (2, 3, 3, 3))
# Add some 255 values (ignore mask)
ssc_target[0, 0, 0, 0] = 255
ssc_target[1, 1, 1, 1] = 255

ARGS = {
    "pred": pred,
    "ssc_target": ssc_target,
    "semantic": True
}
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 0, dtype family float, shape () — shape () 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
get_ray_marching_ray Ran
ran; our contract draft was wrong, not the code
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("0b6e05dede932a3d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

gridcloud3d Ran
ran, honoured the contract we drafted
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("544ddd0593aad265")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

hourglass_PSMNet Ran
ran on a synthesized input
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("7e67c3ab9712def5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

matmul2 Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from ganwanshui/simpleoccupancy
pointer only; the stored copy get_code serves, from ganwanshui/simpleoccupancy, is pointer only (licence: NONE) · get_code("c9c44e261dffcaf1")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

merge_intrinsics Ran
ran; our contract draft was wrong, not the code
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("bb084b6163c5dd5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

meshgrid3d Ran
ran, honoured the contract we drafted
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("a4928c855659636c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_grid2d Ran
ran; our contract draft was wrong, not the code
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("0c090b7d5948bb66")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reduce_masked_mean Ran
ran; our contract draft was wrong, not the code
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("7183abcbcac9bc28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

safe_inverse Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("0330f0652735d8cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

scale_intrinsics Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("4ce19a7b18b72a50")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sem_scal_loss Ran
ran; our contract draft was wrong, not the code
weiyithu/SurroundOcc/projects/mmdet3d_plugin/surroundocc/loss/loss_utils.py
code served (permissive licence) · get_code("d062b8e225df0d31")
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 0, dtype family float, shape () 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
import torch.nn.functional as F

torch.manual_seed(0)

# Analyze the function requirements:
# - pred: shape (batch, n_classes, D1, D2, D3) - 5D tensor, softmax applied on dim 1
# - ssc_target: shape (batch, D1, D2, D3) - 4D tensor with class indices, 255 is mask value
# - Operations: indexing, masking, comparing to class indices, sum operations

# Build small tensors with distinct dimensions for clarity
batch_size = 2
n_classes = 4
d1, d2, d3 = 3, 5, 7

# pred: logits before softmax, shape (batch, n_classes, d1, d2, d3)
pred = torch.randn(batch_size, n_classes, d1, d2, d3)

# ssc_target: class indices (0 to n_classes-1) and 255 for invalid voxels
# shape (batch, d1, d2, d3)
ssc_target = torch.randint(0, n_classes, (batch_size, d1, d2, d3))
# Add some 255 values to create mask variation
ssc_target[0, 0, 0, 0] = 255
ssc_target[1, 1, 2, 3] = 255

ARGS = {
    "pred": pred,
    "ssc_target": ssc_target,
}
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 0, dtype family float, shape () — shape () 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
split_intrinsics Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("ab0432e202897c24")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Density Not yet run
unverified (harvested, no recorded run)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("92f2770d1abea929")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

S3DCNN Not yet run
unverified (harvested, no recorded run)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("fb671695776a2c4b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

VolumeDecoder Not yet run
unverified (harvested, no recorded run)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("e2e54f6438dc01eb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Vox_util Not yet run
unverified (harvested, no recorded run)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("5cac58ebf82c0097")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

extract_simpleocc_mesh Not yet run
unverified (harvested, no recorded run)
ganwanshui/simpleoccupancy/networks/occupancy_decoder.py
pointer only (licence: NONE) · get_code("3ce0c6c6df84b076")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ganwanshui/simpleoccupancy when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

multiscale_supervision Not yet run
unverified (harvested, no recorded run)
weiyithu/SurroundOcc/projects/mmdet3d_plugin/surroundocc/loss/loss_utils.py
code served (permissive licence) · get_code("0ed1a1d33b9b9bfc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 3 later) and 20 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
sem_scal_loss 4 other papers
2 dated earlier, 2 later
2112.00726 (2021-12)
MonoScene: Monocular 3D Semantic Scene Completion
2302.13540 (2023-02)
OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
2305.16133 (2023-05)
OVO: Open-Vocabulary Occupancy
and 1 more not named here
convbn_3d
brick of this paper's assembly: helper
2 other papers
2 later
2312.09243 (2023-12)
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments
Gan_GaussianOcc_Fully_Self-supervised_and_Efficient_3D_Occupancy_Estimation_with_Gaussian_ICCV_2025_paper (2025 (year only))
GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting
matmul2
brick of this paper's assembly: helper
2 other papers
1 the same month, 1 later
2303.10076 (2023-03)
A Simple Framework for 3D Occupancy Estimation in Autonomous Driving
2407.16124 (2024-07)
Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos
Density
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2207.09686 (2022-07)
Object-Compositional Neural Implicit Surfaces

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 scene understanding plays a vital role in visionbased autonomous driving. While most existing methods focus on 3D object detection, they have difficulty describing real-world objects of arbitrary shapes and infinite classes. Towards a more comprehensive perception of a 3D scene, in this paper, we propose a SurroundOcc method to predict the 3D occupancy with multi-camera images. We first extract multi-scale features for each image and adopt spatial 2D-3D attention to lift them to the 3D volume space. Then we apply 3D convolutions to progressively upsample the volume features and impose supervision on multiple levels. To obtain dense occupancy prediction, we design a pipeline to generate dense occupancy ground truth without expansive occupancy annotations. Specifically, we fuse multi-frame LiDAR scans of dynamic objects and static scenes separately. Then we adopt Poisson Reconstruction to fill the holes and voxelize the mesh to get dense occupancy labels. Extensive experiments on nuScenes and SemanticKITTI datasets demonstrate the superiority of our method. Code and dataset are available at https://github.com/weiyithu/SurroundOcc.

For agents

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

get_harvested_code_for_paper("2303.09551")
get_code_for_paper("2303.09551")
have("2303.09551")

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

curl https://syntology.ai/api/ran/2303.09551.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.09551.svg)](https://syntology.ai/paper/2303.09551)

Connect an agent — have() is free.