# ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image

arXiv: https://arxiv.org/abs/1909.01106 · HTML: https://mlsanity.com/paper/1909.01106/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2019.

## Built on by (most cited first, 30 of 32)

- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception](https://mlsanity.com/paper/2303.03991/) (2023)
- [SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction](https://mlsanity.com/paper/2311.12754/) (2023)
- [Symphonize 3D Semantic Scene Completion with Contextual Instance Queries](https://mlsanity.com/paper/2306.15670/) (2023)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers](https://mlsanity.com/paper/2301.04545/) (2023)
- [Semantic Scene Completion via Integrating Instances and Scene in-the-Loop](https://mlsanity.com/paper/2104.03640/) (2021)
- [GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering](https://mlsanity.com/paper/2403.11324/) (2024)
- [PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness](https://mlsanity.com/paper/2312.02158/) (2023)
- [3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views](https://mlsanity.com/paper/2406.04875/) (2024)
- [DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation](https://mlsanity.com/paper/2311.17084/) (2023)
- [SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion](https://mlsanity.com/paper/2306.15349/) (2023)
- [Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective](https://mlsanity.com/paper/2112.12925/) (2021)
- [From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Prediction](https://mlsanity.com/paper/2203.08122/) (2022)
- [Learning Local Displacements for Point Cloud Completion](https://mlsanity.com/paper/2203.16600/) (2022)
- [Semantic Scene Completion with Cleaner Self](https://mlsanity.com/paper/2303.09977/) (2023)
- [IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement](https://mlsanity.com/paper/2106.15413/) (2021)
- [Data Augmented 3D Semantic Scene Completion with 2D Segmentation Priors](https://mlsanity.com/paper/2111.13309/) (2021)
- [SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion](https://mlsanity.com/paper/2508.02261/) (2025)
- [SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning](https://mlsanity.com/paper/2208.08307/) (2022)
- [SSR-2D: Semantic 3D Scene Reconstruction from 2D Images](https://mlsanity.com/paper/2302.03640/) (2023)
- [SoftPool++: An Encoder-Decoder Network for Point Cloud Completion](https://mlsanity.com/paper/2205.03899/) (2022)
- [Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image](https://mlsanity.com/paper/2210.05891/) (2022)
- [Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence](https://mlsanity.com/paper/2312.08054/) (2023)
- [Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes](https://mlsanity.com/paper/2602.22667/) (2026)
- [CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2307.07938/) (2023)
- [Deep Learning for 3D Point Cloud Enhancement: A Survey](https://mlsanity.com/paper/2411.00857/) (2024)
- [TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion](https://mlsanity.com/paper/2512.00300/) (2025)
- [Self-supervised Latent Space Optimization with Nebula Variational Coding](https://mlsanity.com/paper/2506.01414/) (2025)
- [Fusing RGBD Tracking and Segmentation Tree Sampling for Multi-Hypothesis Volumetric Segmentation](https://mlsanity.com/paper/2104.00205/) (2021)

## Abstract (arXiv)

We propose a novel model for 3D semantic completion from a single depth image, based on a single encoder and three separate generators used to reconstruct different geometric and semantic representations of the original and completed scene, all sharing the same latent space. To transfer information between the geometric and semantic branches of the network, we introduce paths between them concatenating features at corresponding network layers. Motivated by the limited amount of training samples from real scenes, an interesting attribute of our architecture is the capacity to supplement the existing dataset by generating a new training dataset with high quality, realistic scenes that even includes occlusion and real noise. We build the new dataset by sampling the features directly from latent space which generates a pair of partial volumetric surface and completed volumetric semantic surface. Moreover, we utilize multiple discriminators to increase the accuracy and realism of the reconstructions. We demonstrate the benefits of our approach on standard benchmarks for the two most common completion tasks: semantic 3D scene completion and 3D object completion.