Visual SSMs

SSM: State Space Model

Visual state-space models adapt recurrent sequence architectures, especially selective state-space models such as Mamba, to images and video. They turn spatial or temporal features into sequences using directional scans, while newer designs explore bidirectional scans, graphs, clusters, frequency-domain processing, and combinations with CNNs or attention. These approaches are used for classification, segmentation, restoration, depth estimation, and video understanding, with benchmarks spanning natural images, medical scans, and remote sensing. A central tension is how to retain linear-time efficiency without losing local detail, boundary accuracy, or robustness to scan direction and domain shift.

Latest papers

81 papers7 papers in the last four weeks, down 36% on the four weeks before. 0.0% of all new papers.

Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics
Jul 3, 2026Anvitha Ramachandran, Dhruv Parikh, Haoyang Fan +2Visual SSMs State Space Models
University of Southern California · DEVCOM Army Research Office
MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model
Jul 3, 2026Wanshu Fan, Xiangyu Li, Cong Wang +4Low-Light Image Enhancement Visual SSMs
National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University, Dalian, China · Hong Kong Polytechnic University, Hong Kong, China · School of Computer Science and Technology, Dalian University of Technology Dalian, China +1
Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection
Jun 25, 2026Ke Chen, Ling Zhou, Guangqi Jiang +3Salient Object Detection Visual SSMs
School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, Jiangsu, 213159, China · College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, 200082, China · Faculty of Data Science, City University of Macau, Avenida Padre Tomás Pereira2026 Taipa, Macao, 999078, China
State Space Models Meet Remote Sensing: A Survey
Jun 24, 2026Qinzhe Yang, Chenyang Liu, Jia Xu +2Remote Sensing Visual SSMs
Shen Yuan Honors College, Beihang University, Beijing 100191, China · Department of Aerospace Intelligent Science and Technology, School of Astronautics, Beihang University, Beijing 100191, China · State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China +1
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Jun 18, 2026Jindi Lv, Aoyu Li, Yuhao Zhou +6Visual SSMs Visual Token Pruning
Sichuan University · GigaAI · Tsinghua University
MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality Block
Jun 16, 2026Hao-Yuan Ma, Li Zhang, Minjie Qiang +1Object Counting Visual SSMs
School of Computer Science and Technology, Soochow University, Suzhou, China
MamBOA: State-Space Architecture for Video Recognition
Jun 13, 2026Mustafa Bora ÇelikVisual SSMs Video Action Recognition
Ankara Medipol University, Ankara, 06050, Turkey
Echo-Memory: A Controlled Study of Memory in Action World Models
Jun 8, 2026Wayne King, Zeyue Xue, Yuxuan Bian +13Action-Conditioned Video Generation Video Diffusion Models
The University of Hong Kong · Joy Future Academy, JD · The Chinese University of Hong Kong +5
Coarse-to-fine Hierarchical Architecture with Sequential Mamba for Brain Reconstruction
Jun 3, 2026Hoang-Son Vo, Van-Hung Bui, Minh-Huy Mai-Duc +2Hierarchical Representation Learning Visual SSMs
Chonnam National University, Gwangju, Republic of Korea · Vietnam National University - Ho Chi Minh City, University of Science, Vietnam · Institute for Cybersecurity and Digital Technologies, Russia
RPCASSM: Robust PCA State Space Model For Infrared Small Target Detection
Jun 1, 2026Pingping Liu, Aohua Li, Yubing Lu +3Infrared Small Target Detection Visual SSMs
College of Computer Science and Technology, Jilin University, Changchun, Jilin, 130012, China and also with the Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin 130012, China · College of Software, Jilin University, Changchun, 130000, Jilin, China · School of Geosciences, Yangtze University, Wuhan 430100 +1
SP-MoMamba: Superpixel-driven Mixture of State Space Experts for Efficient Image Super-Resolution
May 25, 2026Wenbin Zou, Yawen Cui, Yi Wang +5Visual SSMs Mixture-of-Experts Models
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR · School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation
May 24, 2026Aviral Chharia, Fernando De la TorreMulti-View Consistency 3D Gaussian Splatting
Carnegie Mellon University
MambaDSF: Multi-Scale SSM with Dilated Feature Fusion for Sonar Small Target Detection
May 24, 2026Hui Lin, Jiayi Li, Jing Wang +1Underwater Imaging Small Object Detection
School of Information Science and Engineering, Ocean University of China, Qingdao 266100, China · School of Information and Communication Technology, Griffith University, Nathan, QLD 4111, Australia
Deformba: Vision State Space Model with Adaptive State Fusion
May 20, 2026Hongyu Ke, Jack Morris, Yongkang Liu +4Visual SSMs State Space Models
Department of Computer Science, Georgia State University · University of Tennessee Knoxville · InfoTech Labs, Toyota Motor North America R&D.
SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition
May 14, 2026Sukju Oh, Sukkyu SunSurgical Video Understanding Visual SSMs
Department of Computer Science and Artificial Intelligence, Dongguk University, Seoul 04620, Republic of Korea
FSCM: Frequency-Enhanced Spatial-Spectral Coupled Mamba for Infrared Hyperspectral Image Colorization
May 13, 2026Tingting Liu, Yuan Liu, Guiping Chen +2Hyperspectral Imaging Visual SSMs
School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China · School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, 100083, China · School of Instrument and Electronics, North University of China, Taiyuan, 030051, China
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
May 13, 2026Hongli Liu, Yu Wang, Shengjie ZhaoCross-Modal Representation Learning Few-Shot Learning
School of Computer Science and Technology, Tongji University, Shanghai, China · Engineering Research Center of Key Software Technologies for Smart City Perception and Planning, Ministry of Education
MambaPanoptic: A Vision Mamba-based Structured State Space Framework for Panoptic Segmentation
May 12, 2026Qing Cheng, Damiano Bertolini, Wei Zhang +3Image Segmentation Panoptic Segmentation
Technical University of Munich · Munich Center for Machine Learning (MCML) · Polytechnic University of Milan +3
Interactive State Space Model with Cross-Modal Local Scanning for Depth Super-Resolution
May 12, 2026Chen Wu, Ling Wang, Zhuoran Zheng +4Cross-Modal Representation Learning Visual SSMs
National University of Defense Technology · The Hong Kong University of Science and Technology (Guangzhou) · Sun Yat-sen University +2
TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles
May 12, 2026Sara Shoouri, Morteza Tavakoli Taba, Hun-Seok KimSelective SSMs Visual SSMs
University of Michigan
Can Graphs Help Vision SSMs See Better?
May 11, 2026Dhruv Parikh, Anvitha Ramachandran, Haoyang Fan +3Graph Structure Learning Graph Neural Networks
USC · UT Austin · DEVCOM ARL Army Research Office, USA
Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention
May 11, 2026Yuanyuan Peng, Wen LiRetinal Vessel Segmentation Visual SSMs
School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang, 330000, China
EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction
May 8, 2026Wei Yu, Yunhang QianEvent-Based Vision Image Reconstruction
1Harbin Institute of Technology
ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC
May 6, 2026Yurui Du, Pinhao Song, Yutong Hu +1Visual SSMs Model Predictive Control
KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images, B-3000 Leuven, Belgium · Flanders Make at KU Leuven, B-3000 Leuven, Belgium · KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics, B-3000 Leuven, Belgium
$\text{PKS}^4$ :Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding
Apr 29, 2026Lingjie Zeng, Hailun Zhang, Xiwen Wang +1Visual SSMs Video Action Recognition
College of Computer Science, Sichuan University Chengdu, China
Vision SmolMamba: Spike-Guided Token Pruning for Energy-Efficient Spiking State-Space Vision Models
Apr 28, 2026Dewei Bai, Hongxiang Peng, Yunyun Zeng +3Efficient Neural Network Inference Visual SSMs
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China · College of Computer Science, Sichuan University, Chengdu 610065, China
TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media
Apr 28, 2026Fuchen Zheng, Chengpei Xu, Long Ma +10Image Segmentation Healthcare
University of Macau · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Dalian University of Technology +4
BVI-Mamba: Video Enhancement Using a Visual State-Space Model for Low-Light and Underwater Environments
Apr 26, 2026Guoxi Huang, Ruirui Lin, Yini Li +2Underwater Imaging Low-Light Image Enhancement
Visual Information Laboratory, University of Bristol, Bristol, UK
Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation
Apr 25, 2026Sheng-Wei Chan, Hsin-Jui Pan, Chun-Po Shen +3Efficient Semantic Segmentation Visual SSMs
Department of Electrical and Computer Engineering, Tamkang University
Beyond ZOH: Advanced Discretization Strategies for Vision Mamba
Apr 22, 2026Fady Ibrahim, Guangjun Liu, Guanghui WangVisual SSMs State Space Models
Toronto Metropolitan University, 350 Victoria St, Toronto, ON M5B 2K3

Jul 3, 2026J/K move · Enter open · S save

Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics

Anvitha Ramachandran, Dhruv Parikh, Haoyang Fan, Rajgopal Kannan+1

University of Southern California · DEVCOM Army Research Office

Visual SSMs State Space Models

Open paper AskPDF arXiv

State Space Models (SSMs) have emerged as an alternative to Vision Transformers, yet most vision SSMs inherit directional token scanning from causal sequence modeling. While effective for sequential data, directional scanning introduces spatial bias and orientation-sensitive representations. We present Vision Non-Causal Trapezoidal Mamba (VNCT), a second-order non-causal vision SSM that enables all image tokens to interact in a single pass, eliminating direSctional scanning and achieving low single-image inference latency. VNCT exhibits more orientation-robust representations, showing reduced performance degradation under image rotations and flips, while improving Boundary IoU by up to 3.7 points, leading to more accurate boundary preservation and object localization. Across ImageNet-1K classification, COCO object detection and instance segmentation, and ADE20K semantic segmentation, VNCT consistently outperforms both directional-scanning vision SSMs and first-order non-causal SSMs. These results show that directional scanning is unnecessary for high-performance vision SSMs and that second-order non-causal state-space modeling offers a simple, efficient, and robust alternative for visual recognition.