{"total":56,"rows":[{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144,"area":null},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114,"area":null},{"id":"2412.06699","title":"You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale","created":"2024-12-09","cited_by_count":65,"area":"diffusion"},{"id":"2404.16112","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","created":"2024-04-24","cited_by_count":64,"area":"ssm"},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2409.08270","title":"FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally","created":"2024-09-12","cited_by_count":58,"area":null},{"id":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54,"area":"ssm"},{"id":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50,"area":"ssm"},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45,"area":"ssm"},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41,"area":"ssm"},{"id":"2412.09043","title":"DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving","created":"2024-12-12","cited_by_count":29,"area":"wm"},{"id":"2406.06367","title":"MVGamba: Unify 3D Content Generation as State Space Sequence Modeling","created":"2024-06-10","cited_by_count":23,"area":"diffusion"},{"id":"2406.18462","title":"GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality","created":"2024-06-26","cited_by_count":18,"area":null},{"id":"2410.03105","title":"Mamba in Vision: A Comprehensive Survey of Techniques and Applications","created":"2024-10-04","cited_by_count":18,"area":"ssm"},{"id":"2410.08190","title":"Poison-splat: Computation Cost Attack on 3D Gaussian Splatting","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2501.14317","title":"Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation","created":"2025-01-24","cited_by_count":18,"area":null},{"id":"2503.19913","title":"PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model","created":"2025-03-25","cited_by_count":15,"area":"wm"},{"id":"2408.11758","title":"MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs","created":"2024-08-21","cited_by_count":14,"area":"ssm"},{"id":"2503.06235","title":"StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams","created":"2025-03-08","cited_by_count":14,"area":null},{"id":"2506.09565","title":"SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2602.20160","title":"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction","created":"2026-02-23","cited_by_count":12,"area":null},{"id":"2406.13099","title":"Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models","created":"2024-06-18","cited_by_count":10,"area":"diffusion"},{"id":"2410.08567","title":"Diffusion-Based Depth Inpainting for Transparent and Reflective Objects","created":"2024-10-11","cited_by_count":9,"area":null},{"id":"2506.03118","title":"HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2506.08862","title":"StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2408.10575","title":"MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval","created":"2024-08-20","cited_by_count":7,"area":"ssm"},{"id":"2502.03465","title":"Seeing World Dynamics in a Nutshell","created":"2025-02-05","cited_by_count":7,"area":null},{"id":"2504.13159","title":"Digital Twin Generation from Visual Data: A Survey","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2509.24209","title":"Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2409.07040","title":"Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement","created":"2024-09-11","cited_by_count":6,"area":null},{"id":"2412.14579","title":"GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splatting","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2502.15130","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","created":"2025-02-21","cited_by_count":6,"area":"ssm"},{"id":"2505.17966","title":"Is Single-View Mesh Reconstruction Ready for Robotics?","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2502.14895","title":"High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2503.01448","title":"Generative Human Geometry Distribution","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2406.09850","title":"GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View Diffusion","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2504.01512","title":"High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model","created":"2025-04-02","cited_by_count":4,"area":null},{"id":"2508.03118","title":"H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2509.16552","title":"ST-GS: Vision-Based 3D Semantic Occupancy Prediction with Spatial-Temporal Gaussian Splatting","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2404.16323","title":"LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians","created":"2024-04-25","cited_by_count":3,"area":null},{"id":"2404.19394","title":"CLIP-Mamba: CLIP Pretrained Mamba Models with OOD and Hessian Evaluation","created":"2024-04-30","cited_by_count":3,"area":"ssm"},{"id":"2410.13195","title":"UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2508.13287","title":"InnerGS: Internal Scenes Reconstruction and Segmentation via Factorized 3D Gaussian Splatting","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2509.04406","title":"Few-step Flow for 3D Generation via Marginal-Data Transport Distillation","created":"2025-09-04","cited_by_count":3,"area":"diffusion"},{"id":"2509.25603","title":"GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2411.18135","title":"ModeDreamer: Mode Guiding Score Distillation for Text-to-3D Generation using Reference Image Prompts","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2508.21542","title":"Complete Gaussian Splats from a Single Image with Denoising Diffusion Models","created":"2025-08-29","cited_by_count":2,"area":"diffusion"},{"id":"2607.16624","title":"SPARE-GS: Structural Parsimony and Resource Efficiency for 3D Gaussian Splatting","created":"2026-07-18","cited_by_count":2,"area":null},{"id":"2407.02109","title":"HRSAM: Efficient Interactive Segmentation in High-Resolution Images","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2409.12193","title":"Vista3D: Unravel the 3D Darkside of a Single Image","created":"2024-09-18","cited_by_count":1,"area":"diffusion"},{"id":"2502.10475","title":"X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2605.25220","title":"Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2505.20904","title":"HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion","created":"2025-05-27","cited_by_count":0,"area":"ssm"},{"id":"2608.29929","title":"Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}