FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion
- 9 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 7524-7531
Abstract
Semantic Scene Completion (SSC) from monocular RGB images is a fundamental yet challenging task due to the inherent ambiguity of inferring occluded 3D geometry from a single view. While feed-forward methods have made progress, they often struggle to generate plausible details in occluded regions and preserve the fundamental spatial relationships of objects. Such accurate generative reasoning capability for the entire 3D space is critical in real-world applications. In this paper, we present FlowSSC, the first generative framework applied directly to monocular semantic scene completion. FlowSSC treats the SSC task as a conditional generation problem and can seamlessly integrate with existing feed-forward SSC methods to significantly boost their performance. To achieve real-time inference without compromising quality, we introduce Shortcut Flow-matching that operates in a compact triplane latent space. Unlike standard diffusion models that require hundreds of steps, our method utilizes a shortcut mechanism to achieve high-fidelity generation in a single step, enabling practical deployment in autonomous systems. Extensive experiments on SemanticKITTI demonstrate that FlowSSC achieves state-of-the-art performance, significantly outperforming existing baselines.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Symphonize 3D Semantic Scene Completion with Contextual Instance Queries2024
- Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions2023
- OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction2023
- Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction2023
- VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion2023
- MonoScene: Monocular 3D Semantic Scene Completion2022
- Diffusion Probabilistic Models for 3D Point Cloud Generation2021
- Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution2020
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences2019
- Semantic Scene Completion from a Single Depth Image2017