ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splatting

• URL: http://arxiv.org/abs/2509.16552v1
• Date: Sat, 20 Sep 2025 06:36:30 GMT
• Title: ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splatting
• Authors: Xiaoyang Yan, Muleilan Pei, Shaojie Shen,
• Abstract summary: 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.
• Score: 21.87807066521776
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D occupancy prediction is critical for comprehensive scene understanding in vision-centric autonomous driving. Recent advances have explored utilizing 3D semantic Gaussians to model occupancy while reducing computational overhead, but they remain constrained by insufficient multi-view spatial interaction and limited multi-frame temporal consistency. To overcome these issues, in this paper, we propose a novel Spatial-Temporal Gaussian Splatting (ST-GS) framework to enhance both spatial and temporal modeling in existing Gaussian-based pipelines. Specifically, we develop a guidance-informed spatial aggregation strategy within a dual-mode attention mechanism to strengthen spatial interaction in Gaussian representations. Furthermore, we introduce a geometry-aware temporal fusion scheme that effectively leverages historical context to improve temporal continuity in scene completion. Extensive experiments on the large-scale nuScenes occupancy prediction benchmark showcase that our proposed approach not only achieves state-of-the-art performance but also delivers markedly better temporal consistency compared to existing Gaussian-based methods.

Related papers

• Learning Multi-Modal Mobility Dynamics for Generalized Next Location Recommendation [51.00494428978262]
  We leverage multi-modal spatial-temporal knowledge to characterize mobility dynamics for the location recommendation task.<n>First, we construct a unified spatial-temporal relational graph (STRG) for multi-modal representation.<n>Second, we design a gating mechanism to fuse spatial-temporal graph representations of different modalities.
  arXiv  Detail & Related papers  (2025-12-27T14:23:04Z)
• RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion [64.49056527678606]
  We propose a Token-wise Attention integrated into not only the U-Net diffusion model but also the radar-temporal encoder.<n>Unlike prior approaches, our method integrates attention into the architecture without incurring the high resource cost typical of pixel-space diffusion.<n>Our experiments and evaluations demonstrate that the proposed method significantly outperforms state-of-the-art approaches, robustness local fidelity, generalization, and superior in complex precipitation forecasting scenarios.
  arXiv  Detail & Related papers  (2025-10-16T17:59:13Z)
• A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction [33.28893562327803]
  RAST achieves superior performance while maintaining efficiency in large-scale datasets.<n>Our framework consists of three key designs: 1) Decoupled and Query Retriever to capture decoupled temporal features and construct residual fusion via Retrieval-Augmented Generation (RAG); 2) Universal Backbone Predict Storeor that accommodates pre-trained ST-GNNs or simple predictors; and 3) Universal Backbone Predict Storeor that accommodates pre-trained ST-GNNs or simple predictors.
  arXiv  Detail & Related papers  (2025-08-14T10:11:39Z)
• Transformer with Koopman-Enhanced Graph Convolutional Network for Spatiotemporal Dynamics Forecasting [12.301897782320967]
  TK-GCN is a two-stage framework that integrates geometry-aware spatial encoding with long-range temporal modeling.<n>We show that TK-GCN consistently delivers superior predictive accuracy across a range of forecast horizons.
  arXiv  Detail & Related papers  (2025-07-05T01:26:03Z)
• 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)
• Geometry-aware Active Learning of Spatiotemporal Dynamic Systems [4.251030047034566]
  This paper proposes a geometry-aware active learning framework for modeling dynamic systems.<n>We develop an adaptive active learning strategy to strategically identify spatial locations for data collection and further maximize the prediction accuracy.
  arXiv  Detail & Related papers  (2025-04-26T19:56:38Z)
• Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction [62.69089767730514]
  We present GDFusion, a temporal fusion method for vision-based 3D semantic occupancy prediction (VisionOcc)<n>It opens up the underexplored aspects of temporal fusion within the VisionOcc framework, focusing on both temporal cues and fusion strategies.
  arXiv  Detail & Related papers  (2025-04-17T14:05:33Z)
• Sequential Gaussian Avatars with Hierarchical Motion Context [7.6736633105043515]
  SMPL-driven 3DGS human avatars struggle to capture fine appearance details due to complex mapping from pose to appearance during fitting.<n>We propose SeqAvatar, which excavates the explicit 3DGS representation to better model human avatars based on a hierarchical motion context.<n>Our method significantly outperforms 3DGS-based approaches and renders human avatars rendering orders of magnitude faster than the latest NeRF-based models.
  arXiv  Detail & Related papers  (2024-11-25T04:05:19Z)
• DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes [71.61083731844282]
  We present DeSiRe-GS, a self-supervised gaussian splatting representation.<n>It enables effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.
  arXiv  Detail & Related papers  (2024-11-18T05:49:16Z)
• STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Video [7.345621536750547]
  This paper presents the S-Temporal GraphFormer framework (STGFormer) for 3D human pose estimation in videos.<n>First, we introduce a STG attention mechanism, designed to more effectively leverage the inherent graph distributions of human body.<n>Next, we present a Modulated Hop-wise Regular GCN to independently process temporal and spatial dimensions in parallel.<n>Finally, we demonstrate our method state-of-the-art performance on the Human3.6M and MPIINF-3DHP datasets.
  arXiv  Detail & Related papers  (2024-07-14T06:45:27Z)
• Triplet Attention Transformer for Spatiotemporal Predictive Learning [9.059462850026216]
  We propose an innovative triplet attention transformer designed to capture both inter-frame dynamics and intra-frame static features. The model incorporates the Triplet Attention Module (TAM), which replaces traditional recurrent units by exploring self-attention mechanisms in temporal, spatial, and channel dimensions.
  arXiv  Detail & Related papers  (2023-10-28T12:49:33Z)
• Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition [79.33539539956186]
  We propose a simple method to disentangle multi-scale graph convolutions and a unified spatial-temporal graph convolutional operator named G3D. By coupling these proposals, we develop a powerful feature extractor named MS-G3D based on which our model outperforms previous state-of-the-art methods on three large-scale datasets.
  arXiv  Detail & Related papers  (2020-03-31T11:28:25Z)
• A Spatial-Temporal Attentive Network with Spatial Continuity for Trajectory Prediction [74.00750936752418]
  We propose a novel model named spatial-temporal attentive network with spatial continuity (STAN-SC) First, spatial-temporal attention mechanism is presented to explore the most useful and important information. Second, we conduct a joint feature sequence based on the sequence and instant state information to make the generative trajectories keep spatial continuity.
  arXiv  Detail & Related papers  (2020-03-13T04:35:50Z)

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.