# LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures

arXiv: https://arxiv.org/abs/2511.10209 · HTML: https://mlsanity.com/paper/2511.10209/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 13 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [GRNet: Gridding Residual Network for Dense Point Cloud Completion](https://mlsanity.com/paper/2006.03761/) (2020)
- [Anisotropic Convolutional Networks for 3D Semantic Scene Completion](https://mlsanity.com/paper/2004.02122/) (2020)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths](https://mlsanity.com/paper/2012.03408/) (2020)
- [SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer](https://mlsanity.com/paper/2207.10315/) (2022)
- [Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion](https://mlsanity.com/paper/2203.09780/) (2022)
- [AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers](https://mlsanity.com/paper/2301.04545/) (2023)
- [Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion](https://mlsanity.com/paper/2403.13470/) (2024)
- [Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer](https://mlsanity.com/paper/2202.09367/) (2022)
- [LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR](https://mlsanity.com/paper/2302.14052/) (2023)
- [Decompositional Neural Scene Reconstruction with Generative Diffusion Prior](https://mlsanity.com/paper/2503.14830/) (2025)
- [CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers](https://mlsanity.com/paper/2401.01552/) (2024)
- [SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization](https://mlsanity.com/paper/2503.14558/) (2025)
- [Volumetric Occupancy Mapping With Probabilistic Depth Completion for Robotic Navigation](https://mlsanity.com/paper/2012.03023/) (2020)
- [SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field](https://mlsanity.com/paper/2403.14366/) (2024)
- [LiDPM: Rethinking Point Diffusion for Lidar Scene Completion](https://mlsanity.com/paper/2504.17791/) (2025)
- [GenPC: Zero-shot Point Cloud Completion via 3D Generative Priors](https://mlsanity.com/paper/2502.19896/) (2025)

## Built on by (most cited first, 2 of 2)

- [CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain](https://mlsanity.com/paper/2606.16048/) (2026)
- [Towards Real-Time and Adaptable LiDAR Scene Completion](https://mlsanity.com/paper/2608.16490/) (2026)

## Abstract (arXiv)

3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models for high-fidelity reconstruction. However, their multi-step iterative sampling incurs significant computational overhead, limiting its real-time applicability. To address this, we propose LiNeXt-a lightweight, non-diffusion network optimized for rapid and accurate point cloud completion. Specifically, LiNeXt first applies the Noise-to-Coarse (N2C) Module to denoise the input noisy point cloud in a single pass, thereby obviating the multi-step iterative sampling of diffusion-based methods. The Refine Module then takes the coarse point cloud and its intermediate features from the N2C Module to perform more precise refinement, further enhancing structural completeness. Furthermore, we observe that LiDAR point clouds exhibit a distance-dependent spatial distribution, being densely sampled at proximal ranges and sparsely sampled at distal ranges. Accordingly, we propose the Distance-aware Selected Repeat strategy to generate a more uniformly distributed noisy point cloud. On the SemanticKITTI dataset, LiNeXt achieves a 199.8x speedup in inference, reduces Chamfer Distance by 50.7%, and uses only 6.1% of the parameters compared with LiDiff. These results demonstrate the superior efficiency and effectiveness of LiNeXt for real-time scene completion.