Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

• URL: http://arxiv.org/abs/2603.12255v1
• Date: Thu, 12 Mar 2026 17:58:58 GMT
• Title: Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
• Abstract summary: We propose Spatial-TTT towards streaming visual-based spatial intelligence with test-time training (TTT)<n>We design a hybrid architecture and adopt large-temporal updates parallel with sliding-window attention for efficient spatial video processing.<n>Experiments demonstrate that Spatial-TTT improves long-horizon spatial understanding and achieves state-of-the-art performance on video spatial benchmarks.
• Score: 61.6942259866261
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial intelligence. The core challenge is not simply longer context windows but how spatial information is selected, organized, and retained over time. In this paper, we propose Spatial-TTT towards streaming visual-based spatial intelligence with test-time training (TTT), which adapts a subset of parameters (fast weights) to capture and organize spatial evidence over long-horizon scene videos. Specifically, we design a hybrid architecture and adopt large-chunk updates parallel with sliding-window attention for efficient spatial video processing. To further promote spatial awareness, we introduce a spatial-predictive mechanism applied to TTT layers with 3D spatiotemporal convolution, which encourages the model to capture geometric correspondence and temporal continuity across frames. Beyond architecture design, we construct a dataset with dense 3D spatial descriptions, which guides the model to update its fast weights to memorize and organize global 3D spatial signals in a structured manner. Extensive experiments demonstrate that Spatial-TTT improves long-horizon spatial understanding and achieves state-of-the-art performance on video spatial benchmarks. Project page: https://liuff19.github.io/Spatial-TTT.

Related papers

• Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors [54.51965288351254]
  We present an online 3D vision-language model that enables real-time spatial understanding from streaming video.<n>Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token prediction to learn when to respond.<n>To address the scarcity of streaming 3D-language data, we further develop a scalable data generation pipeline.
  arXiv  Detail & Related papers  (2026-06-05T04:16:24Z)
• SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding [64.86119288520419]
  multimodal language models struggle with spatial reasoning across time and space.<n>We present SIMS-V -- a systematic data-generation framework that leverages the privileged information of 3D simulators.<n>Our approach demonstrates robust generalization, maintaining performance on general video understanding while showing substantial improvements on embodied and real-world spatial tasks.
  arXiv  Detail & Related papers  (2025-11-06T18:53:31Z)
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence [13.168559963356952]
  We present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations.<n>Our key insight is to unleash the strong structure prior to the feed-forward visual geometry foundation model.<n>A connector then integrates both features into unified visual tokens for enhanced spatial understanding.
  arXiv  Detail & Related papers  (2025-05-29T17:59:04Z)
• ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models [63.12671761097701]
  Vision-Language Models (Ms) struggle to analyze elements like traveled distance and speed of moving objects.<n>We construct a benchmark dataset referred to as STKit and ST-Bench.<n>We show that ST-VLM generalizes robustly across diverse domains and tasks.
  arXiv  Detail & Related papers  (2025-03-25T05:08:06Z)
• SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability [58.46310813774538]
  Large language models (LMLMs) have made remarkable progress in either temporal or spatial localization.<n>However they struggle to perform-temporal video grounding.<n>This limitation stems from two major challenges.<n>We introduce SpaceLM, a MLLMVL endowed with temporal-temporal video grounding.
  arXiv  Detail & Related papers  (2025-03-18T07:40:36Z)
• STF: Spatial Temporal Fusion for Trajectory Prediction [18.359362362173098]
  Trajectory prediction is a challenging task that aims to predict the future trajectory of vehicles or pedestrians over a short time horizon.<n>The more information the model can capture, the more precise the future trajectory can be predicted.<n>In this study, we introduce an integrated 3D graph that incorporates both spatial and temporal edges.
  arXiv  Detail & Related papers  (2023-11-29T23:31:40Z)
• Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos [10.50306784245168]
  We present atemporal tendency reasoning (STR) network for recovering human body pose shape from videos. Our STR aims to learn accurate and spatial motion sequences in an unconstrained environment. Our STR remains competitive with the state-of-the-art on three datasets.
  arXiv  Detail & Related papers  (2022-10-07T16:09:07Z)
• Spatio-Temporal Self-Attention Network for Video Saliency Prediction [13.873682190242365]
  3D convolutional neural networks have achieved promising results for video tasks in computer vision. We propose a novel Spatio-Temporal Self-Temporal Self-Attention 3 Network (STSANet) for video saliency prediction.
  arXiv  Detail & Related papers  (2021-08-24T12:52:47Z)
• Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos [78.45050529204701]
  We propose a novel framework to pursue discriminative and robust representation by modeling cross-scale spatial-temporal correlation. CTL utilizes a CNN backbone and a key-points estimator to extract semantic local features from human body. It explores a context-reinforced topology to construct multi-scale graphs by considering both global contextual information and physical connections of human body.
  arXiv  Detail & Related papers  (2021-04-15T14:32:12Z)

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.