# Adversarial Semantic Scene Completion from a Single Depth Image

arXiv: https://arxiv.org/abs/1810.10901 · HTML: https://mlsanity.com/paper/1810.10901/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2018.

## Built on by (most cited first, 9 of 9)

- [UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation](https://mlsanity.com/paper/2311.01448/) (2023)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [Scene Synthesis via Uncertainty-Driven Attribute Synchronization](https://mlsanity.com/paper/2108.13499/) (2021)
- [IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement](https://mlsanity.com/paper/2106.15413/) (2021)
- [Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image](https://mlsanity.com/paper/2210.05891/) (2022)
- [CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2307.07938/) (2023)
- [HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity](https://mlsanity.com/paper/2506.23854/) (2025)
- [Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completion](https://mlsanity.com/paper/2203.09167/) (2022)
- [3D GANs and Latent Space: A comprehensive survey](https://mlsanity.com/paper/2304.03932/) (2023)

## Abstract (arXiv)

We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image. We improve the accuracy of the regressed semantic 3D maps by a novel architecture based on adversarial learning. In particular, we suggest using multiple adversarial loss terms that not only enforce realistic outputs with respect to the ground truth, but also an effective embedding of the internal features. This is done by correlating the latent features of the encoder working on partial 2.5D data with the latent features extracted from a variational 3D auto-encoder trained to reconstruct the complete semantic scene. In addition, differently from other approaches that operate entirely through 3D convolutions, at test time we retain the original 2.5D structure of the input during downsampling to improve the effectiveness of the internal representation of our model. We test our approach on the main benchmark datasets for semantic scene completion to qualitatively and quantitatively assess the effectiveness of our proposal.