mlsanityData to 7 Oct 2026

Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completion

arXiv 2203.09167 ↗First posted 17 Mar 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Scene Completion is the task of completing missing geometry from a partial scan of a scene. Most previous methods compute an implicit representation from range data using a Truncated Signed Distance Function (T-SDF) computed on a 3D grid as input to neural networks. The truncation decreases but does not remove the border errors introduced by the sign of SDF for open surfaces. As an alternative, we present an Unsigned Distance Function (UDF) as an input representation to scene completion neural networks. The proposed UDF is simple, and efficient as a geometry representation, and can be computed on any point cloud. In contrast to usual Signed Distance Functions, our UDF does not require normal computation. To obtain the explicit geometry, we present a method for extracting a point cloud from discretized UDF values on a sparse grid. We compare different SDFs and UDFs for the scene completion task on indoor and outdoor point clouds collected using RGB-D and LiDAR sensors and show improved completion using the proposed UDF function.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

34 of 54 references.

References · 34

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  2. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  4. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2020Convolutional Occupancy Networkscited by 760
  8. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  9. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  10. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  11. 2018PCN: Point Completion Networkcited by 382
  12. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
22 more
  1. 2019Neural Point-Based Graphicscited by 326
  2. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  3. 2017Submanifold Sparse Convolutional Networkscited by 223
  4. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  5. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 187
  6. 2016Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planningcited by 148
  7. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  8. 2021Variational Relational Point Completion Networkcited by 103
  9. 2020S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Cloudscited by 102
  10. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  11. 20213D Semantic Scene Completion: a Surveycited by 74
  12. 2020Generative Sparse Detection Networks for 3D Single-shot Object Detectioncited by 69
  13. 2019Efficient Semantic Scene Completion Network with Spatial Group Convolutioncited by 66
  14. 2019Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completioncited by 43
  15. 2018IMLS-SLAM: scan-to-model matching based on 3D datacited by 40
  16. 2020SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scanscited by 34
  17. 2021Orienting Point Clouds with Dipole Propagationcited by 31
  18. 2018View-volume Network for Semantic Scene Completion from a Single Depth Imagecited by 26
  19. 2021Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mappingcited by 25
  20. 2020DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfacescited by 16
  21. 20193D Semantic Scene Completion from a Single Depth Image using Adversarial Trainingcited by 11
  22. 2018Adversarial Semantic Scene Completion from a Single Depth Imagecited by 9

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representationscited by 2