Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model

• URL: http://arxiv.org/abs/2510.00862v1
• Date: Wed, 01 Oct 2025 13:11:13 GMT
• Title: Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model
• Authors: Hyun-kyu Ko, Youbin Kim, Jihyeon Park, Dongheok Park, Gyeongjin Kang, Wonjun Cho, Hyung Yi, Eunbyung Park,
• Abstract summary: State Space Models (SSMs) have historically played a central role in sequential modeling.<n>Recent advances in selective SSMs like Mamba offer a compelling alternative.<n>We propose a hybrid architecture that combines shifted window self-attention for spatial context aggregation with Mamba-based selective scanning for efficient temporal propagation.
• Score: 15.551773379039675
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated due to their ability to model global context, their quadratic complexity and limited scalability make them less suited for long sequences. Video super-resolution (VSR) methods have traditionally relied on recurrent architectures to propagate features across frames. However, such approaches suffer from well-known issues including vanishing gradients, lack of parallelism, and slow inference speed. Recent advances in selective SSMs like Mamba offer a compelling alternative: by enabling input-dependent state transitions with linear-time complexity, Mamba mitigates these issues while maintaining strong long-range modeling capabilities. Despite this potential, Mamba alone struggles to capture fine-grained spatial dependencies due to its causal nature and lack of explicit context aggregation. To address this, we propose a hybrid architecture that combines shifted window self-attention for spatial context aggregation with Mamba-based selective scanning for efficient temporal propagation. Furthermore, we introduce Gather-Scatter Mamba (GSM), an alignment-aware mechanism that warps features toward a center anchor frame within the temporal window before Mamba propagation and scatters them back afterward, effectively reducing occlusion artifacts and ensuring effective redistribution of aggregated information across all frames. The official implementation is provided at: https://github.com/Ko-Lani/GSMamba.

Related papers

• TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition [59.99922360648663]
  TSkel-Mamba is a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics.<n>The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition.
  arXiv  Detail & Related papers  (2025-12-12T11:55:16Z)
• MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition [42.21383693511854]
  We propose motion-aware state fusion linear mamba (MSF-Mamba) for microture recognition.<n>MSF-Mamba enhances Mamba with localtemporal modeling by contextual local neighboring states.<n>Our design introduces a motion-aware state fusion module based on central frame difference (CFD)<n>Specifically, MSF-Mamba supports multiscale motion-aware state fusion, as well as an adaptive scale weighting module.
  arXiv  Detail & Related papers  (2025-10-12T07:16:58Z)
• Mamba Modulation: On the Length Generalization of Mamba [34.91142589654215]
  Mamba is a leading architecture for state-space language models.<n>We show that Mamba's performance significantly deteriorates when applied to contexts longer than those seen during pre-training.<n>We propose an approach that applies spectrum scaling to pre-trained Mamba models to enable robust long-context generalization.
  arXiv  Detail & Related papers  (2025-09-23T22:46:19Z)
• Trajectory-aware Shifted State Space Models for Online Video Super-Resolution [57.87099307245989]
  This paper presents a novel online VSR method based on Trajectory-aware Shifted SSMs (TS-Mamba)<n>TS-Mamba first constructs the trajectories within a video to select the most similar tokens from the previous frames.<n>Our TS-Mamba achieves state-of-the-art performance in most cases and over 22.7% reduction complexity (in MACs)
  arXiv  Detail & Related papers  (2025-08-14T08:42:15Z)
• AtrousMamaba: An Atrous-Window Scanning Visual State Space Model for Remote Sensing Change Detection [29.004019252136565]
  We propose a novel model, AtrousMamba, which balances the extraction of fine-grained local details with the integration of global contextual information.<n>By leveraging the atrous window scan visual state space (AWVSS) module, we design dedicated end-to-end Mamba-based frameworks for binary change detection (BCD) and semantic change detection (SCD)<n> Experimental results on six benchmark datasets show that the proposed framework outperforms existing CNN-based, Transformer-based, and Mamba-based methods.
  arXiv  Detail & Related papers  (2025-07-22T02:36:16Z)
• EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction [66.84997711357101]
  EventMamba is a specialized model designed for event-based video reconstruction tasks.<n>We show that EventMamba markedly improves speed while delivering superior visual quality compared to Transformer-based methods.
  arXiv  Detail & Related papers  (2025-03-25T14:46:45Z)
• STNMamba: Mamba-based Spatial-Temporal Normality Learning for Video Anomaly Detection [48.997518615379995]
  Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems.<n>Most existing methods based on CNNs and transformers still suffer from substantial computational burdens.<n>We propose a lightweight and effective Mamba-based network named STNMamba to enhance the learning of spatial-temporal normality.
  arXiv  Detail & Related papers  (2024-12-28T08:49:23Z)
• SIGMA: Selective Gated Mamba for Sequential Recommendation [56.85338055215429]
  Mamba, a recent advancement, has exhibited exceptional performance in time series prediction.<n>We introduce a new framework named Selective Gated Mamba ( SIGMA) for Sequential Recommendation.<n>Our results indicate that SIGMA outperforms current models on five real-world datasets.
  arXiv  Detail & Related papers  (2024-08-21T09:12:59Z)
• LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba [54.85262314960038]
  Local Attentional Mamba blocks capture both global contexts and local details with linear complexity. Our model exhibits exceptional scalability and surpasses the performance of DiT across various model scales on ImageNet at 256x256 resolution. Compared to state-of-the-art diffusion models on ImageNet 256x256 and 512x512, our largest model presents notable advantages, such as a reduction of up to 62% GFLOPs.
  arXiv  Detail & Related papers  (2024-08-05T16:39:39Z)

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.