mlsanityData to 7 Oct 2026

Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion

arXiv 2006.03762 ↗First posted 6 Jun 2020cs.CV cs.GRcited by 33

Not on the map. Why?

Abstract (arXiv)

Acquiring complete and clean 3D shape and scene data is challenging due to geometric occlusion and insufficient views during 3D capturing. We present a simple yet effective deep learning approach for completing the input noisy and incomplete shapes or scenes. Our network is built upon the octree-based CNNs (O-CNN) with U-Net like structures, which enjoys high computational and memory efficiency and supports to construct a very deep network structure for 3D CNNs. A novel output-guided skip-connection is introduced to the network structure for better preserving the input geometry and learning geometry prior from data effectively. We show that with these simple adaptions -- output-guided skip-connection and deeper O-CNN (up to 70 layers), our network achieves state-of-the-art results in 3D shape completion and semantic scene computation.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 5; 2023: 6; 2024: 7; 2025: 3; 2026: 3.

33 papers.

Sort:

  1. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  2. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 129
  3. 20213D Semantic Scene Completion: a Surveycited by 74
  4. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  5. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  6. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  7. 2021Multiresolution Deep Implicit Functions for 3D Shape Representationcited by 35
  8. 2021Fast and Explicit Neural View Synthesiscited by 28
  9. 2023Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mappingcited by 27
  10. 2021OctField: Hierarchical Implicit Functions for 3D Modelingcited by 25
  11. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  12. 2025ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Graspingcited by 13
21 more
  1. 2022CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusioncited by 11
  2. 2024Zero-Shot Multi-Object Scene Completioncited by 9
  3. 2021Object Wake-up: 3D Object Rigging from a Single Imagecited by 8
  4. 2022Semi-supervised 3D shape segmentation with multilevel consistency and part substitutioncited by 8
  5. 2023SSR-2D: Semantic 3D Scene Reconstruction from 2D Imagescited by 7
  6. 2024Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priorscited by 7
  7. 2022Free-form 3D Scene Inpainting with Dual-stream GANcited by 6
  8. 2023Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Modelcited by 5
  9. 2025RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completioncited by 5
  10. 2021CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scenecited by 4
  11. 2024LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimationcited by 3
  12. 2024Joint Point Cloud Upsampling and Cleaning with Octree-based CNNscited by 3
  13. 2021Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networkscited by 2
  14. 2022Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentationcited by 2
  15. 2024Oriented-grid Encoder for 3D Implicit Representationscited by 2
  16. 2026MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decodingcited by 2
  17. 2023Tensorformer: Normalized Matrix Attention Transformer for High-quality Point Cloud Reconstructioncited by 1
  18. 2024Surface Reconstruction from Point Clouds via Grid-based Intersection Predictioncited by 1
  19. 2025Self-supervised Latent Space Optimization with Nebula Variational Codingcited by 1
  20. 2026GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priorscited by 1
  21. 2026CAOA -- Completion-Assisted Object-CAD Alignmentcited by 0