# S4C: Self-Supervised Semantic Scene Completion with Neural Fields

arXiv: https://arxiv.org/abs/2310.07522 · HTML: https://mlsanity.com/paper/2310.07522/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 70 of its 90 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 30 of 70)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera](https://mlsanity.com/paper/1910.02527/) (2019)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023)

## Built on by (most cited first, 28 of 28)

- [GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting](https://mlsanity.com/paper/2408.11447/) (2024)
- [GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding](https://mlsanity.com/paper/2412.13193/) (2024)
- [Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation](https://mlsanity.com/paper/2404.11958/) (2024)
- [OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments](https://mlsanity.com/paper/2312.09243/) (2023)
- [MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations](https://mlsanity.com/paper/2311.11762/) (2023)
- [Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles](https://mlsanity.com/paper/2402.07635/) (2024)
- [GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow](https://mlsanity.com/paper/2502.17288/) (2025)
- [Neural Radiance Field in Autonomous Driving: A Survey](https://mlsanity.com/paper/2404.13816/) (2024)
- [Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion](https://mlsanity.com/paper/2507.06230/) (2025)
- [Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving](https://mlsanity.com/paper/2403.08504/) (2024)
- [Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review](https://mlsanity.com/paper/2402.11141/) (2024)
- [LeAP: Consistent multi-domain 3D labeling using Foundation Models](https://mlsanity.com/paper/2502.03901/) (2025)
- [Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation](https://mlsanity.com/paper/2404.07933/) (2024)
- [GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splatting](https://mlsanity.com/paper/2412.14579/) (2024)
- [ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation](https://mlsanity.com/paper/2511.15396/) (2025)
- [OccAny: Generalized Unconstrained Urban 3D Occupancy](https://mlsanity.com/paper/2603.23502/) (2026)
- [OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective](https://mlsanity.com/paper/2512.20770/) (2025)
- [Event-aided Semantic Scene Completion](https://mlsanity.com/paper/2502.02334/) (2025)
- [RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation](https://mlsanity.com/paper/2502.14792/) (2025)
- [SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion](https://mlsanity.com/paper/2503.16825/) (2025)
- [IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals](https://mlsanity.com/paper/2506.20671/) (2025)
- [Out-of-Distribution Semantic Occupancy Prediction](https://mlsanity.com/paper/2506.21185/) (2025)
- [YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos](https://mlsanity.com/paper/2506.18266/) (2025)
- [Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images](https://mlsanity.com/paper/2508.02323/) (2025)
- [VOCA: Visual Odometry with Codec Awareness](https://mlsanity.com/paper/2607.00189/) (2026)
- [Lift, Splat, Map: Lifting Foundation Masks for Label-Free Semantic Scene Completion](https://mlsanity.com/paper/2407.03425/) (2024)
- [Faster Training, Fewer Labels: Self-Supervised Pretraining for Fine-Grained BEV Segmentation](https://mlsanity.com/paper/2602.18066/) (2026)
- [GNFormer: Gaussian Neural Field Transformer for Efficient Camera-based Occupancy Prediction](https://mlsanity.com/paper/2610.15522/) (2026)

## Abstract (arXiv)

3D semantic scene understanding is a fundamental challenge in computer vision. It enables mobile agents to autonomously plan and navigate arbitrary environments. SSC formalizes this challenge as jointly estimating dense geometry and semantic information from sparse observations of a scene. Current methods for SSC are generally trained on 3D ground truth based on aggregated LiDAR scans. This process relies on special sensors and annotation by hand which are costly and do not scale well. To overcome this issue, our work presents the first self-supervised approach to SSC called S4C that does not rely on 3D ground truth data. Our proposed method can reconstruct a scene from a single image and only relies on videos and pseudo segmentation ground truth generated from off-the-shelf image segmentation network during training. Unlike existing methods, which use discrete voxel grids, we represent scenes as implicit semantic fields. This formulation allows querying any point within the camera frustum for occupancy and semantic class. Our architecture is trained through rendering-based self-supervised losses. Nonetheless, our method achieves performance close to fully supervised state-of-the-art methods. Additionally, our method demonstrates strong generalization capabilities and can synthesize accurate segmentation maps for far away viewpoints.