SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.04384 · 2024

GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 3 failures 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/2412.04384.json · badge: /api/ran/2412.04384.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/gaussianformer canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
CE_ssc_loss Ran
ran; our contract draft was wrong, not the code
huang-yh/gaussianformer/loss/occupancy_loss.py
pointer only (licence: NONE); the stored copy get_code serves, from wzzheng/gaussianad, is pointer only (licence: NONE) · get_code("b18df7ddccd09c7f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, huang-yh/gaussianformer 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.

CE_wo_softmax Ran
ran; our contract draft was wrong, not the code
huang-yh/gaussianformer/loss/occupancy_loss.py
pointer only (licence: NOASSERTION) · get_code("0c03b43e79b10f0b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, huang-yh/gaussianformer (NOASSERTION). 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.

get_grid_coords Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
huang-yh/gaussianformer/vis.py
pointer only (licence: NONE) · get_code("fb05e5a5654edb4e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, huang-yh/gaussianformer 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.

inverse_sigmoid Not yet run
unverified (harvested, no recorded run)
huang-yh/gaussianformer/loss/occupancy_loss.py
pointer only (licence: NONE); the stored copy get_code serves, from wzzheng/gaussianad, is pointer only (licence: NONE) · get_code("15715bd88c8ed092")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, huang-yh/gaussianformer 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 3 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.

FunctionAlso present inEarliest-datedOthers named
get_grid_coords 4 other papers
1 dated earlier, 2 the same month, 1 same year, order not determinable
2311.16038 (2023-11)
OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving
02024 (2024 (year only))
OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving
2412.10371 (2024-12)
GaussianAD: Gaussian-Centric End-to-End Autonomous Driving
and 1 more not named here
CE_ssc_loss 1 other paper
1 the same month
2412.10371 (2024-12)
GaussianAD: Gaussian-Centric End-to-End Autonomous Driving
inverse_sigmoid 1 other paper
1 the same month
2412.10371 (2024-12)
GaussianAD: Gaussian-Centric End-to-End Autonomous Driving

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 semantic occupancy prediction is an important task for robust vision-centric autonomous driving, which predicts fine-grained geometry and semantics of the surrounding scene. Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes. Although 3D semantic Gaussian serves as an object-centric sparse alternative, most of the Gaussians still describe the empty region with low efficiency. To address this, we propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its neighborhood being occupied and conforms to probabilistic multiplication to derive the overall geometry. Furthermore, we adopt the exact Gaussian mixture model for semantics calculation to avoid unnecessary overlapping of Gaussians. To effectively initialize Gaussians in non-empty region, we design a distribution-based initialization module which learns the pixel-aligned occupancy distribution instead of the depth of surfaces. We conduct extensive experiments on nuScenes and KITTI-360 datasets and our GaussianFormer-2 achieves state-of-the-art performance with high efficiency. Code: https://github.com/huang-yh/GaussianFormer.

For agents

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

get_harvested_code_for_paper("2412.04384")
get_code_for_paper("2412.04384")
have("2412.04384")

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

curl https://syntology.ai/api/ran/2412.04384.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.04384.svg)](https://syntology.ai/paper/2412.04384)

Connect an agent — have() is free.