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

arXiv: https://arxiv.org/abs/2006.03762 · HTML: https://mlsanity.com/paper/2006.03762/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2020.

## Built on by (most cited first, 30 of 33)

- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [Locally Attentional SDF Diffusion for Controllable 3D Shape Generation](https://mlsanity.com/paper/2305.04461/) (2023)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations](https://mlsanity.com/paper/2205.02825/) (2022)
- [InfiniCity: Infinite-Scale City Synthesis](https://mlsanity.com/paper/2301.09637/) (2023)
- [Deep Implicit Moving Least-Squares Functions for 3D Reconstruction](https://mlsanity.com/paper/2103.12266/) (2021)
- [Multiresolution Deep Implicit Functions for 3D Shape Representation](https://mlsanity.com/paper/2109.05591/) (2021)
- [Fast and Explicit Neural View Synthesis](https://mlsanity.com/paper/2107.05775/) (2021)
- [Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping](https://mlsanity.com/paper/2306.01405/) (2023)
- [OctField: Hierarchical Implicit Functions for 3D Modeling](https://mlsanity.com/paper/2111.01067/) (2021)
- [Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping](https://mlsanity.com/paper/2407.14225/) (2024)
- [ZeroGrasp: Zero-Shot Shape Reconstruction Enabled Robotic Grasping](https://mlsanity.com/paper/2504.10857/) (2025)
- [CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion](https://mlsanity.com/paper/2211.13702/) (2022)
- [Zero-Shot Multi-Object Scene Completion](https://mlsanity.com/paper/2403.14628/) (2024)
- [Object Wake-up: 3D Object Rigging from a Single Image](https://mlsanity.com/paper/2108.02708/) (2021)
- [Semi-supervised 3D shape segmentation with multilevel consistency and part substitution](https://mlsanity.com/paper/2204.08824/) (2022)
- [SSR-2D: Semantic 3D Scene Reconstruction from 2D Images](https://mlsanity.com/paper/2302.03640/) (2023)
- [Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors](https://mlsanity.com/paper/2410.19680/) (2024)
- [Free-form 3D Scene Inpainting with Dual-stream GAN](https://mlsanity.com/paper/2212.08464/) (2022)
- [Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Model](https://mlsanity.com/paper/2302.06557/) (2023)
- [RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion](https://mlsanity.com/paper/2506.05285/) (2025)
- [CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene](https://mlsanity.com/paper/2111.12905/) (2021)
- [LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation](https://mlsanity.com/paper/2404.03925/) (2024)
- [Joint Point Cloud Upsampling and Cleaning with Octree-based CNNs](https://mlsanity.com/paper/2410.17001/) (2024)
- [Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks](https://mlsanity.com/paper/2107.02909/) (2021)
- [Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation](https://mlsanity.com/paper/2208.04766/) (2022)
- [Oriented-grid Encoder for 3D Implicit Representations](https://mlsanity.com/paper/2402.06752/) (2024)
- [MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decoding](https://mlsanity.com/paper/2601.03660/) (2026)
- [Tensorformer: Normalized Matrix Attention Transformer for High-quality Point Cloud Reconstruction](https://mlsanity.com/paper/2306.15989/) (2023)
- [Surface Reconstruction from Point Clouds via Grid-based Intersection Prediction](https://mlsanity.com/paper/2403.14085/) (2024)

## 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.