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

arXiv: https://arxiv.org/abs/2410.15674 · HTML: https://mlsanity.com/paper/2410.15674/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 30 of 31)

- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2304.14365/) (2023)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds](https://mlsanity.com/paper/2012.09242/) (2020)
- [SCPNet: Semantic Scene Completion on Point Cloud](https://mlsanity.com/paper/2303.06884/) (2023)
- [MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2204.12667/) (2022)
- [SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving](https://mlsanity.com/paper/2306.09001/) (2023)
- [Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data](https://mlsanity.com/paper/2011.09141/) (2020)
- [What You See is What You Get: Exploiting Visibility for 3D Object Detection](https://mlsanity.com/paper/1912.04986/) (2019)
- [Efficient Semantic Scene Completion Network with Spatial Group Convolution](https://mlsanity.com/paper/1907.05091/) (2019)
- [Two Stream 3D Semantic Scene Completion](https://mlsanity.com/paper/1804.03550/) (2018)
- [Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds](https://mlsanity.com/paper/2109.11453/) (2021)
- [TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation](https://mlsanity.com/paper/2303.09870/) (2023)
- [MATE: Masked Autoencoders are Online 3D Test-Time Learners](https://mlsanity.com/paper/2211.11432/) (2022)
- [Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learning](https://mlsanity.com/paper/2308.16481/) (2023)
- [DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds](https://mlsanity.com/paper/1811.11397/) (2018)
- [Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2303.10457/) (2023)
- [Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributions](https://mlsanity.com/paper/2010.12239/) (2020)
- [DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization](https://mlsanity.com/paper/2212.06331/) (2022)
- [Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving](https://mlsanity.com/paper/2403.08504/) (2024)

## Built on by (most cited first, 12 of 12)

- [OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera](https://mlsanity.com/paper/2511.03571/) (2025)
- [Event-aided Semantic Scene Completion](https://mlsanity.com/paper/2502.02334/) (2025)
- [Enhancing 3D Semantic Scene Completion with a Refinement Module](https://mlsanity.com/paper/2512.18363/) (2025)
- [Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation](https://mlsanity.com/paper/2604.10950/) (2026)
- [Out-of-Distribution Semantic Occupancy Prediction](https://mlsanity.com/paper/2506.21185/) (2025)
- [Exploring Easy Boosts for Lidar Semantic Scene Completion](https://mlsanity.com/paper/2606.03992/) (2026)
- [Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models](https://mlsanity.com/paper/2511.15311/) (2025)
- [FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model](https://mlsanity.com/paper/2606.20110/) (2026)
- [Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation](https://mlsanity.com/paper/2606.20196/) (2026)
- [Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute](https://mlsanity.com/paper/2608.06014/) (2026)
- [Generative Semantic Scene Completion](https://mlsanity.com/paper/2608.26737/) (2026)
- [SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion](https://mlsanity.com/paper/2609.17413/) (2026)

## Abstract (arXiv)

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.