# Towards Real-Time and Adaptable LiDAR Scene Completion

arXiv: https://arxiv.org/abs/2608.16490 · HTML: https://mlsanity.com/paper/2608.16490/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [3D Shape Generation and Completion through Point-Voxel Diffusion](https://mlsanity.com/paper/2104.03670/) (2021)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers](https://mlsanity.com/paper/2207.02202/) (2022)
- [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023)
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://mlsanity.com/paper/2108.04444/) (2021)
- [UnO: Unsupervised Occupancy Fields for Perception and Forecasting](https://mlsanity.com/paper/2406.08691/) (2024)
- [Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion](https://mlsanity.com/paper/2403.13470/) (2024)
- [ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers](https://mlsanity.com/paper/2405.04299/) (2024)
- [Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data](https://mlsanity.com/paper/2301.00527/) (2023)
- [LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR](https://mlsanity.com/paper/2302.14052/) (2023)
- [SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection](https://mlsanity.com/paper/2307.11477/) (2023)
- [Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion](https://mlsanity.com/paper/2412.03515/) (2024)
- [LiDPM: Rethinking Point Diffusion for Lidar Scene Completion](https://mlsanity.com/paper/2504.17791/) (2025)
- [Multi-View Attentive Contextualization for Multi-View 3D Object Detection](https://mlsanity.com/paper/2405.12200/) (2024)
- [LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures](https://mlsanity.com/paper/2511.10209/) (2025)
- [LiFlow: Flow Matching for 3D LiDAR Scene Completion](https://mlsanity.com/paper/2602.02232/) (2026)
- [I2PRef: Image-Driven Point Completion with Iterative Refinement](https://mlsanity.com/paper/2605.26914/) (2026)

## Abstract (arXiv)

LiDAR scene completion is a key component of 3D perception in autonomous driving, where the scene must be completed in real time to be usable in downstream tasks. Existing approaches typically follow an initialize-and-refine paradigm, in which a coarse initialization of the scene is first constructed, then refined into complete 3D geometry. Generative models are slower because they iteratively refine random Gaussian noise into the scene, while non-generative methods perturb the partial scene with a fixed noise scale, which limits coverage of large gaps and occluded regions and requires manual recalibration for each new sensor configuration. We present RapidLiDAR, a LiDAR scene completion method that treats the initialization itself as a learned, data-driven component. We propose an adaptive initialization module that predicts a spatially varying displacement for each partial input point, expanding the partial observations into a coarse scene initialization adapted to the local geometry, without requiring manual noise tuning. To refine this coarse initialization into a complete and coherent scene, we additionally propose a multi-scale reconstruction module that further refines point positions by querying multi-scale 3D voxel and 2D BEV feature maps constructed from the input scan. By replacing point-neighborhood operators such as farthest point sampling and k-nearest neighbor search with voxel- and BEV-based feature extraction, our architecture is faster and can handle different input resolutions by design. Experiments on SemanticKITTI and KITTI-360 show that our method achieves completion performance on par with the state of the art while completing a full scene in 0.1 seconds, which is 2.3 times faster than the fastest prior method. This matches the 10 Hz acquisition rate of typical automotive LiDAR sensors, taking a step toward real-time LiDAR scene completion.