CVAug 4, 2025

SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion

arXiv:2508.02261v14 citationsh-index: 12
Originality Incremental advance
AI Analysis

This work addresses inefficiencies in 3D scene reconstruction for computer vision applications, representing an incremental improvement over existing object-centric methods.

The paper tackles the problem of inefficient initialization and outlier artifacts in monocular 3D Semantic Scene Completion by proposing SplatSSC, which uses depth-guided initialization and a decoupled aggregator to achieve state-of-the-art performance with improvements of over 6.3% in IoU and 4.1% in mIoU on the Occ-ScanNet dataset.

Monocular 3D Semantic Scene Completion (SSC) is a challenging yet promising task that aims to infer dense geometric and semantic descriptions of a scene from a single image. While recent object-centric paradigms significantly improve efficiency by leveraging flexible 3D Gaussian primitives, they still rely heavily on a large number of randomly initialized primitives, which inevitably leads to 1) inefficient primitive initialization and 2) outlier primitives that introduce erroneous artifacts. In this paper, we propose SplatSSC, a novel framework that resolves these limitations with a depth-guided initialization strategy and a principled Gaussian aggregator. Instead of random initialization, SplatSSC utilizes a dedicated depth branch composed of a Group-wise Multi-scale Fusion (GMF) module, which integrates multi-scale image and depth features to generate a sparse yet representative set of initial Gaussian primitives. To mitigate noise from outlier primitives, we develop the Decoupled Gaussian Aggregator (DGA), which enhances robustness by decomposing geometric and semantic predictions during the Gaussian-to-voxel splatting process. Complemented with a specialized Probability Scale Loss, our method achieves state-of-the-art performance on the Occ-ScanNet dataset, outperforming prior approaches by over 6.3% in IoU and 4.1% in mIoU, while reducing both latency and memory consumption by more than 9.3%. The code will be released upon acceptance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes