SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.15674 · NeurIPS · 2024

TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight

Kuk-Jin Yoon, Hyun-Kurl Jang, Jihun Kim, Hyeokjun Kweon

arXiv · PDF · Open in the Atlas

Code that ran

14 of 17 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; 3 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 9 failures of our instrument; 3 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/2410.15674.json · badge: /api/ran/2410.15674.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
blue-531/TALoS canonical (classifier label)
classifier basis: census
11 ran · 3 no recorded run
blue-531/talos canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
SemKITTI2train Ran
ran, violated the contract we drafted
blue-531/TALoS/dataloader/pc_dataset.py
pointer only (licence: NONE) · get_code("f3d8ca81e8d0ee0c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

extract_nonzero_features Ran
ran; our contract draft was wrong, not the code
blue-531/TALoS/network/segmentator_3d_asymm_spconv_unlock.py
pointer only (licence: NONE) · get_code("3f9a651be8d4082c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

frame_transform_scan Ran
ran, honoured the contract we drafted
blue-531/TALoS/dataloader/dataset_semantickitti.py
pointer only (licence: NONE) · get_code("3d6928be33f7d1bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

get_remap_first Ran
ran; our contract draft was wrong, not the code
blue-531/talos/run_tta_val.py
pointer only (licence: NONE) · get_code("261283216054e8b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/talos 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.

get_remap_second Ran
ran, honoured the contract we drafted
blue-531/talos/run_tta_val.py
pointer only (licence: NONE) · get_code("03a862c1bc4bb8d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/talos 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.

iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
blue-531/TALoS/utils/lovasz_losses.py
pointer only (licence: NONE) · get_code("d94639b28b2134ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

iou_binary Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
blue-531/TALoS/utils/lovasz_losses.py
pointer only (licence: NONE) · get_code("1211530cd527bd0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

lovasz_grad Ran
ran, violated the contract we drafted
blue-531/TALoS/utils/lovasz_losses.py
pointer only (licence: NONE) · get_code("e85b5d21dc5b8382")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

manual_extraction Ran
ran; our contract draft was wrong, not the code
blue-531/TALoS/network/segmentator_3d_asymm_spconv_unlock.py
pointer only (licence: NONE) · get_code("1ff14b65ece70b32")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

no_extraction Ran
ran; our contract draft was wrong, not the code
blue-531/TALoS/network/segmentator_3d_asymm_spconv_unlock.py
pointer only (licence: NONE) · get_code("936c2117da625a10")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

register_dataset Ran
ran; our contract draft was wrong, not the code
blue-531/TALoS/dataloader/dataset_semantickitti.py
pointer only (licence: NONE) · get_code("c134fed586d67760")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

register_dataset Ran
ran; our contract draft was wrong, not the code
blue-531/TALoS/dataloader/pc_dataset.py
pointer only (licence: NONE) · get_code("06a0e2786c57fc38")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

register_model Ran
ran; our contract draft was wrong, not the code
blue-531/TALoS/network/cylinder_spconv_3d_unlock.py
pointer only (licence: NONE) · get_code("9416a0d63c5a653a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

train2SemKITTI Ran
ran, honoured the contract we drafted
blue-531/talos/run_tta_val.py
pointer only (licence: NONE) · get_code("ae0ede157bf07297")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/talos 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.

from_voxel_to_voxel Not yet run
unverified (harvested, no recorded run)
blue-531/TALoS/dataloader/dataset_semantickitti.py
pointer only (licence: NONE) · get_code("0a96d3b0c027f68e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

get_model_class Not yet run
unverified (harvested, no recorded run)
blue-531/TALoS/network/cylinder_spconv_3d_unlock.py
pointer only (licence: NONE) · get_code("237978845d0ee378")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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.

get_pc_model_class Not yet run
unverified (harvested, no recorded run)
blue-531/TALoS/dataloader/pc_dataset.py
pointer only (licence: NONE) · get_code("dc3115f6b6438996")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, blue-531/TALoS 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 3 later) and 8 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
lovasz_grad 40 other papers
32 dated earlier, 6 later, 2 same year, order not determinable · 1 only as an assembly brick
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
and 37 more not named here
iou 24 other papers
20 dated earlier, 3 later, 1 same year, order not determinable
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
2003.10778 (2020-03)
PanNuke Dataset Extension, Insights and Baselines
and 21 more not named here
iou_binary 24 other papers
20 dated earlier, 3 later, 1 same year, order not determinable
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
2003.10778 (2020-03)
PanNuke Dataset Extension, Insights and Baselines
and 21 more not named here
get_model_class 2 other papers
2 dated earlier
2109.05441 (2021-09)
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
2208.00223 (2022-08)
PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
register_model 2 other papers
2 dated earlier
2109.05441 (2021-09)
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
2208.00223 (2022-08)
PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
SemKITTI2train 1 other paper
1 dated earlier
2308.01686 (2023-08)
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment
get_pc_model_class 1 other paper
1 dated earlier
2301.00970 (2023-01)
Benchmarking the Robustness of LiDAR Semantic Segmentation Models
register_dataset 1 other paper
1 dated earlier
2301.00970 (2023-01)
Benchmarking the Robustness of LiDAR Semantic Segmentation Models
register_dataset 1 other paper
1 dated earlier
2301.00970 (2023-01)
Benchmarking the Robustness of LiDAR Semantic Segmentation Models

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

Semantic Scene Completion (SSC) aims to perform geometric completion and semantic segmentation simultaneously. Despite the promising results achieved by existing studies, the inherently ill-posed nature of the task presents significant challenges in diverse driving scenarios. This paper introduces TALoS, a novel test-time adaptation approach for SSC that excavates the information available in driving environments. Specifically, we focus on that observations made at a certain moment can serve as Ground Truth (GT) for scene completion at another moment. Given the characteristics of the LiDAR sensor, an observation of an object at a certain location confirms both 1) the occupation of that location and 2) the absence of obstacles along the line of sight from the LiDAR to that point. TALoS utilizes these observations to obtain self-supervision about occupancy and emptiness, guiding the model to adapt to the scene in test time. In a similar manner, we aggregate reliable SSC predictions among multiple moments and leverage them as semantic pseudo-GT for adaptation. Further, to leverage future observations that are not accessible at the current time, we present a dual optimization scheme using the model in which the update is delayed until the future observation is available. Evaluations on the SemanticKITTI validation and test sets demonstrate that TALoS significantly improves the performance of the pre-trained SSC model. Our code is available at https://github.com/blue-531/TALoS. * denotes equal contribution. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).

For agents

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

get_harvested_code_for_paper("2410.15674")
get_code_for_paper("2410.15674")
have("2410.15674")

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

curl https://syntology.ai/api/ran/2410.15674.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.15674.svg)](https://syntology.ai/paper/2410.15674)

Connect an agent — have() is free.