# LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR

arXiv: https://arxiv.org/abs/2302.14052 · HTML: https://mlsanity.com/paper/2302.14052/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 27 Feb 2023.

## Builds on (most cited first, 30 of 36)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [BSP-Net: Generating Compact Meshes via Binary Space Partitioning](https://mlsanity.com/paper/1911.06971/) (2019)
- [Vision-Only Robot Navigation in a Neural Radiance World](https://mlsanity.com/paper/2110.00168/) (2021)
- [BACON: Band-limited Coordinate Networks for Multiscale Scene Representation](https://mlsanity.com/paper/2112.04645/) (2021)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2007.08488/) (2020)
- [3D Neural Scene Representations for Visuomotor Control](https://mlsanity.com/paper/2107.04004/) (2021)
- [SuMa++: Efficient LiDAR-based Semantic SLAM](https://mlsanity.com/paper/2105.11320/) (2021)
- [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://mlsanity.com/paper/2103.06422/) (2021)
- [DiGS : Divergence guided shape implicit neural representation for unoriented point clouds](https://mlsanity.com/paper/2106.10811/) (2021)
- [Learning to Act Properly: Predicting and Explaining Affordances from Images](https://mlsanity.com/paper/1712.07576/) (2017)
- [Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data](https://mlsanity.com/paper/2105.08971/) (2021)
- [Curriculum DeepSDF](https://mlsanity.com/paper/2003.08593/) (2020)
- [A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI](https://mlsanity.com/paper/2003.02371/) (2020)
- [Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform](https://mlsanity.com/paper/2008.09162/) (2020)
- [RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction](https://mlsanity.com/paper/2011.14744/) (2020)
- [Learning Models as Functionals of Signed-Distance Fields for Manipulation Planning](https://mlsanity.com/paper/2110.00792/) (2021)
- [MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Square](https://mlsanity.com/paper/2102.03771/) (2021)
- [TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation](https://mlsanity.com/paper/2210.10775/) (2022)
- [Efficient Continuous-Time SLAM for 3D Lidar-Based Online Mapping](https://mlsanity.com/paper/1810.06802/) (2018)
- [Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing](https://mlsanity.com/paper/2111.12608/) (2021)

## Built on by (most cited first, 30 of 31)

- [MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving](https://mlsanity.com/paper/2307.15058/) (2023)
- [Context and Geometry Aware Voxel Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2405.13675/) (2024)
- [MonoOcc: Digging into Monocular Semantic Occupancy Prediction](https://mlsanity.com/paper/2403.08766/) (2024)
- [Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation](https://mlsanity.com/paper/2404.11958/) (2024)
- [Camera-based 3D Semantic Scene Completion with Sparse Guidance Network](https://mlsanity.com/paper/2312.05752/) (2023)
- [Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion](https://mlsanity.com/paper/2403.13470/) (2024)
- [DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation](https://mlsanity.com/paper/2311.17084/) (2023)
- [Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2303.01212/) (2023)
- [3D Implicit Transporter for Temporally Consistent Keypoint Discovery](https://mlsanity.com/paper/2309.05098/) (2023)
- [FastMAC: Stochastic Spectral Sampling of Correspondence Graph](https://mlsanity.com/paper/2403.08770/) (2024)
- [DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2409.18092/) (2024)
- [SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field](https://mlsanity.com/paper/2403.14366/) (2024)
- [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)
- [Towards Learning to Complete Anything in Lidar](https://mlsanity.com/paper/2504.12264/) (2025)
- [Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion](https://mlsanity.com/paper/2504.11447/) (2025)
- [PosePilot: Steering Camera Pose for Generative World Models with Self-supervised Depth](https://mlsanity.com/paper/2505.01729/) (2025)
- [DPF: Learning Dense Prediction Fields with Weak Supervision](https://mlsanity.com/paper/2303.16890/) (2023)
- [ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera](https://mlsanity.com/paper/2410.11019/) (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)
- [Exploring Easy Boosts for Lidar Semantic Scene Completion](https://mlsanity.com/paper/2606.03992/) (2026)
- [Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss](https://mlsanity.com/paper/2410.11934/) (2024)
- [LISNeRF Mapping: LiDAR-based Implicit Mapping via Semantic Neural Fields for Large-Scale 3D Scenes](https://mlsanity.com/paper/2311.02313/) (2023)
- [VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion](https://mlsanity.com/paper/2512.18954/) (2025)
- [Multi-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completion](https://mlsanity.com/paper/2602.03371/) (2026)
- [PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completion](https://mlsanity.com/paper/2606.03915/) (2026)
- [CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain](https://mlsanity.com/paper/2606.16048/) (2026)
- [FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows](https://mlsanity.com/paper/2607.26645/) (2026)
- [Towards Real-Time and Adaptable LiDAR Scene Completion](https://mlsanity.com/paper/2608.16490/) (2026)

## Abstract (arXiv)

Scene completion refers to obtaining dense scene representation from an incomplete perception of complex 3D scenes. This helps robots detect multi-scale obstacles and analyse object occlusions in scenarios such as autonomous driving. Recent advances show that implicit representation learning can be leveraged for continuous scene completion and achieved through physical constraints like Eikonal equations. However, former Eikonal completion methods only demonstrate results on watertight meshes at a scale of tens of meshes. None of them are successfully done for non-watertight LiDAR point clouds of open large scenes at a scale of thousands of scenes. In this paper, we propose a novel Eikonal formulation that conditions the implicit representation on localized shape priors which function as dense boundary value constraints, and demonstrate it works on SemanticKITTI and SemanticPOSS. It can also be extended to semantic Eikonal scene completion with only small modifications to the network architecture. With extensive quantitative and qualitative results, we demonstrate the benefits and drawbacks of existing Eikonal methods, which naturally leads to the new locally conditioned formulation. Notably, we improve IoU from 31.7% to 51.2% on SemanticKITTI and from 40.5% to 48.7% on SemanticPOSS. We extensively ablate our methods and demonstrate that the proposed formulation is robust to a wide spectrum of implementation hyper-parameters. Codes and models are publicly available at https://github.com/AIR-DISCOVER/LODE.