{"ID":2835073,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00300","arxiv_id":"2512.00300","title":"TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion","abstract":"Embodied 3D Semantic Scene Completion (SSC) infers dense geometry and semantics from continuous egocentric observations. Most existing Gaussian-based methods rely on random initialization of many primitives within predefined spatial bounds, resulting in redundancy and poor scalability to unbounded scenes. Recent depth-guided approach alleviates this issue but remains local, suffering from latency and memory overhead as scale increases. To overcome these challenges, we propose TGSFormer, a scalable Temporal Gaussian Splatting framework for embodied SSC. It maintains a persistent Gaussian memory for temporal prediction, without relying on image coherence or frame caches. For temporal fusion, a Dual Temporal Encoder jointly processes current and historical Gaussian features through confidence-aware cross-attention. Subsequently, a Confidence-aware Voxel Fusion module merges overlapping primitives into voxel-aligned representations, regulating density and maintaining compactness. Extensive experiments demonstrate that TGSFormer achieves state-of-the-art results on both local and embodied SSC benchmarks, offering superior accuracy and scalability with significantly fewer primitives while maintaining consistent long-term scene integrity. The code will be released upon acceptance.","short_abstract":"Embodied 3D Semantic Scene Completion (SSC) infers dense geometry and semantics from continuous egocentric observations. Most existing Gaussian-based methods rely on random initialization of many primitives within predefined spatial bounds, resulting in redundancy and poor scalability to unbounded scenes. Recent depth-...","url_abs":"https://arxiv.org/abs/2512.00300","url_pdf":"https://arxiv.org/pdf/2512.00300v1","authors":"[\"Rui Qian\",\"Haozhi Cao\",\"Tianchen Deng\",\"Tianxin Hu\",\"Weixiang Guo\",\"Shenghai Yuan\",\"Lihua Xie\"]","published":"2025-11-29T03:47:14Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}