# Semantic Scene Completion with Cleaner Self

arXiv: https://arxiv.org/abs/2303.09977 · HTML: https://mlsanity.com/paper/2303.09977/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 69 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Builds on (most cited first, 30 of 42)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Deep Learning is Robust to Massive Label Noise](https://mlsanity.com/paper/1705.10694/) (2017)
- [Anisotropic Convolutional Networks for 3D Semantic Scene Completion](https://mlsanity.com/paper/2004.02122/) (2020)
- [3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior](https://mlsanity.com/paper/2003.14052/) (2020)
- [Feature Pyramid Transformer](https://mlsanity.com/paper/2007.09451/) (2020)
- [Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching](https://mlsanity.com/paper/2102.02973/) (2021)
- [Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data](https://mlsanity.com/paper/2011.09141/) (2020)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [Learning Joint 2D-3D Representations for Depth Completion](https://mlsanity.com/paper/2012.12402/) (2020)
- [Unpaired Deep Image Deraining Using Dual Contrastive Learning](https://mlsanity.com/paper/2109.02973/) (2021)
- [Fair Feature Distillation for Visual Recognition](https://mlsanity.com/paper/2106.04411/) (2021)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion](https://mlsanity.com/paper/1903.00620/) (2019)
- [Semantic Scene Completion via Integrating Instances and Scene in-the-Loop](https://mlsanity.com/paper/2104.03640/) (2021)
- [Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2110.00984/) (2021)
- [Two Stream 3D Semantic Scene Completion](https://mlsanity.com/paper/1804.03550/) (2018)
- [Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion](https://mlsanity.com/paper/1908.00382/) (2019)
- [ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image](https://mlsanity.com/paper/1909.01106/) (2019)
- [RevealNet: Seeing Behind Objects in RGB-D Scans](https://mlsanity.com/paper/1904.12012/) (2019)

## Built on by (most cited first, 12 of 12)

- [Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion](https://mlsanity.com/paper/2412.03515/) (2024)
- [Label-efficient Semantic Scene Completion with Scribble Annotations](https://mlsanity.com/paper/2405.15170/) (2024)
- [Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2501.07260/) (2025)
- [SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion](https://mlsanity.com/paper/2508.02261/) (2025)
- [Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification](https://mlsanity.com/paper/2310.11210/) (2023)
- [Unleashing Network Potentials for Semantic Scene Completion](https://mlsanity.com/paper/2403.07560/) (2024)
- [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)
- [FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction](https://mlsanity.com/paper/2604.28115/) (2026)
- [RWKV-PCSSC: Exploring RWKV Model for Point Cloud Semantic Scene Completion](https://mlsanity.com/paper/2511.09878/) (2025)
- [VioLA: Aligning Videos to 2D LiDAR Scans](https://mlsanity.com/paper/2311.04783/) (2023)
- [Semantic Scene Completion with Multi-Feature Data Balancing Network](https://mlsanity.com/paper/2412.01431/) (2024)

## Abstract (arXiv)

Semantic Scene Completion (SSC) transforms an image of single-view depth and/or RGB 2D pixels into 3D voxels, each of whose semantic labels are predicted. SSC is a well-known ill-posed problem as the prediction model has to "imagine" what is behind the visible surface, which is usually represented by Truncated Signed Distance Function (TSDF). Due to the sensory imperfection of the depth camera, most existing methods based on the noisy TSDF estimated from depth values suffer from 1) incomplete volumetric predictions and 2) confused semantic labels. To this end, we use the ground-truth 3D voxels to generate a perfect visible surface, called TSDF-CAD, and then train a "cleaner" SSC model. As the model is noise-free, it is expected to focus more on the "imagination" of unseen voxels. Then, we propose to distill the intermediate "cleaner" knowledge into another model with noisy TSDF input. In particular, we use the 3D occupancy feature and the semantic relations of the "cleaner self" to supervise the counterparts of the "noisy self" to respectively address the above two incorrect predictions. Experimental results validate that our method improves the noisy counterparts with 3.1% IoU and 2.2% mIoU for measuring scene completion and SSC, and also achieves new state-of-the-art accuracy on the popular NYU dataset.