TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion

• URL: http://arxiv.org/abs/2512.00300v1
• Date: Sat, 29 Nov 2025 03:47:14 GMT
• Title: TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completion
• Abstract summary: Embodied 3D Semantic Scene Completion infers dense geometry and semantics from continuous egocentric observations.<n>Recent depth-guided approach alleviates this issue but remains local, suffering from latency and memory overhead as scale increases.<n>We propose TGSFormer, a scalable Temporal Gaussian Splatting framework for embodied SSC.
• Score: 38.31128137855632
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Feasibility and Memory Mechanisms of Chern-Simons Context Reservoir Computation [0.0]
  We investigate whether a Chern-Simons context reservoir is a viable computational substrate.<n>To separate generic reservoir behavior from gauge-specific effects, we compare four matched models.<n>We find a task-specific advantage for geometry- and order-sensitive processing, rather than generic reservoir superiority.
  arXiv  Detail & Related papers  (2026-09-10T17:45:30Z)
• GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting [71.12303582606019]
  Continuous Video Super-Resolution (C-STVSR) aims to simultaneously enhance the spatial and frame rate of videos by arbitrary scale factors.<n>We propose GS-STVSR, an ultra-efficient C-STVSR framework based on 2D Gaussianting (2D-GS)<n>We show that GS-STVSR achieves state-of-the-art quality across all benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T10:11:05Z)
• TRiGS: Temporal Rigid-Body Motion for Scalable 4D Gaussian Splatting [40.83830884179225]
  TRiGS is a novel 4D representation that utilizes unified, continuous geometric transformations.<n>We show that TRiGS achieves high fidelity rendering on standard benchmarks while uniquely scaling to extended video sequences without severe memory bottlenecks.
  arXiv  Detail & Related papers  (2026-04-01T06:35:13Z)
• S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction [57.07346645250984]
  Streaming Semantic Gaussian Splatting (S2GS) is a strictly causal, incremental 3D Gaussian semantic field framework.<n>It does not leverage future frames and continuously updates scene geometry, appearance, and instance-level semantics without reprocessing historical frames.<n>S2GS matches or outperforms strong offline baselines on joint reconstruction-and-understanding benchmarks.
  arXiv  Detail & Related papers  (2026-03-15T05:48:55Z)
• Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting [79.37674445572462]
  Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends.<n>Treating reshaped tensors as static images results in a topological mismatch.<n> relying on uniform fixed-size representations allocates modeling capacity inefficiently.<n>TimeGS is a novel framework that fundamentally shifts the forecasting paradigm from regression to 2D generative rendering.
  arXiv  Detail & Related papers  (2026-02-10T14:13:36Z)
• SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation [10.295970926059812]
  Visual autoregressive ( VAR) models generate images through next-scale prediction, naturally achieving coarse-to-fine, fast, high-fidelity mirroring human perception.<n>In practice, this hierarchy can drift at inference time, as limited capacity and accumulated error cause the model to deviate from its coarse-to-fine nature.<n>We propose Scaled Spatial Guidance (SSG), training-free, inference-time guidance that steers generation toward the intended hierarchy while maintaining global coherence.
  arXiv  Detail & Related papers  (2026-02-05T10:48:58Z)
• SVRecon: Sparse Voxel Rasterization for Surface Reconstruction [60.92372415355283]
  We extend the recently proposed sparse voxelization paradigm to the task of high-fidelity surface reconstruction by integrating SVRecon.<n>Our method achieves strong reconstruction accuracy while having consistently speedy convergence.
  arXiv  Detail & Related papers  (2025-11-21T16:32:01Z)
• ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives [27.616880434926646]
  3D Gaussian Splatting achieves state-of-the-art image quality and real-time performance in novel view synthesis.<n>Issue stems from cloning-based densification, which propagates Gaussians along existing geometry.<n>We present ConeGS, an image-space-informed densification framework that is independent of existing scene geometry state.
  arXiv  Detail & Related papers  (2025-11-10T07:54:58Z)
• D$^2$GS: Depth-and-Density Guided Gaussian Splatting for Stable and Accurate Sparse-View Reconstruction [73.61056394880733]
  3D Gaussian Splatting (3DGS) enables real-time, high-fidelity novel view synthesis (NVS) with explicit 3D representations.<n>We identify two key failure modes under sparse-view conditions: overfitting in regions with excessive Gaussian density near the camera, and underfitting in distant areas with insufficient Gaussian coverage.<n>We propose a unified framework D$2$GS, comprising two key components: a Depth-and-Density Guided Dropout strategy, and a Distance-Aware Fidelity Enhancement module.
  arXiv  Detail & Related papers  (2025-10-09T17:59:49Z)
• ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splatting [21.87807066521776]
  3D occupancy prediction is critical for comprehensive scene understanding in vision-centric autonomous driving.<n>Recent advances have explored utilizing 3D semantic Gaussians to model occupancy while reducing computational overhead.<n>We propose a novel Spatial-Temporal Gaussian Splatting (ST-GS) framework to enhance both spatial and temporal modeling.
  arXiv  Detail & Related papers  (2025-09-20T06:36:30Z)
• Segmentation-Driven Initialization for Sparse-view 3D Gaussian Splatting [0.9251324073335035]
  3D Gaussian Splatting (3DGS) has enabled real-time rendering with competitive quality.<n>Existing pipelines often rely on Structure-from-Motion (SfM) for camera pose estimation, an approach that struggles in genuinely sparse-view settings.<n>We propose a method that mitigates inefficiency by leveraging region-based segmentation to identify and retain only structurally significant regions.
  arXiv  Detail & Related papers  (2025-09-15T12:31:33Z)
• SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion [31.116931865374564]
  3D Semantic Scene Completion is a challenging yet promising task that aims to infer dense geometric and semantic descriptions of a scene from a single image.<n>We propose SplatSSC, a novel framework that resolves these limitations with a depth-guided initialization strategy and a principled Gaussian aggregator.<n>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.
  arXiv  Detail & Related papers  (2025-08-04T10:09:31Z)
• RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS [79.15416002879239]
  3D Gaussian Splatting has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling.<n>Existing methods struggle with accurately modeling scenes affected by transient objects, leading to artifacts in the rendered images.<n>We propose RobustSplat, a robust solution based on two critical designs.
  arXiv  Detail & Related papers  (2025-06-03T11:13:48Z)
• STDR: Spatio-Temporal Decoupling for Real-Time Dynamic Scene Rendering [15.873329633980015]
  Existing 3DGS-based methods for dynamic reconstruction often suffer from textbfSTDR (Spatio-coupling DeTemporal for Real-time rendering)<n>We propose textbfSTDR (Spatio-coupling DeTemporal for Real-time rendering), a plug-and-play module learns thattemporal probability distributions for each scene.
  arXiv  Detail & Related papers  (2025-05-28T14:26:41Z)
• MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields [100.90743697473232]
  Radiance fields represented by 3D Gaussians excel at synthesizing novel views, offering both high training efficiency and fast rendering.<n>Existing methods often incorporate depth priors from dense estimation networks but overlook the inherent multi-view consistency in input images.<n>We propose a view synthesis framework based on 3D Gaussian Splatting, enabling scene reconstruction from sparse views.
  arXiv  Detail & Related papers  (2024-10-15T08:39:05Z)
• Distributed Stochastic Gradient Descent with Staleness: A Stochastic Delay Differential Equation Based Framework [56.82432591933544]
  Distributed gradient descent (SGD) has attracted considerable recent attention due to its potential for scaling computational resources, reducing training time, and helping protect user privacy in machine learning.<n>This paper presents the run time and staleness of distributed SGD based on delay differential equations (SDDEs) and the approximation of gradient arrivals.<n>It is interestingly shown that increasing the number of activated workers does not necessarily accelerate distributed SGD due to staleness.
  arXiv  Detail & Related papers  (2024-06-17T02:56:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.