Semi-supervised Implicit Scene Completion from Sparse LiDAR
Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations. However, this scheme has not yet been successfully used for LiDAR point cloud data, due to its spatially varying sparsity. In this paper, we develop a novel formulation that conditions the semi-supervised implicit function on localized shape embeddings. It exploits the strong representation learning power of sparse convolutional networks to generate shape-aware dense feature volumes, while still allows semi-supervised signed distance function learning without knowing its exact values at free space. With extensive quantitative and qualitative results, we demonstrate intrinsic properties of this new learning system and its usefulness in real-world road scenes. Notably, we improve IoU from 26.3% to 51.0% on SemanticKITTI. Moreover, we explore two paradigms to integrate semantic label predictions, achieving implicit semantic completion. Code and models can be accessed at https://github.com/OPEN-AIR-SUN/SISC.
Code (1)
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera
Depth completion, the technique of estimating a dense depth image from sparse depth measurements, has a variety of applications in robotics and autonomous driving. However, depth completion faces 3 main challenges: the i…
Autonomous DrivingDepth CompletionSemantic Scene Completion using Local Deep Implicit Functions on LiDAR Data
Semantic scene completion is the task of jointly estimating 3D geometry and semantics of objects and surfaces within a given extent. This is a particularly challenging task on real-world data that is sparse and occluded.…
3D geometry3D Semantic Scene CompletionScene SegmentationNeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising
In recent years, there have been significant advancements in 3D reconstruction and dense RGB-D SLAM systems. One notable development is the application of Neural Radiance Fields (NeRF) in these systems, which utilizes im…
3D ReconstructionDenoisingDepth CompletionDepth Estimation+2LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR
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 autono…
Autonomous DrivingRepresentation LearningCIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions. It is based on an end-to-end sparse convolutional network, CircNet, that jointly…