学术成果

@article{mao2025learning,

title = {Learning Spatial Decay for Vision Transformers},

author = {Yuxin Mao and Zhen Qin and Jinxing Zhou and Bin Fan and Jing Zhang and Yiran Zhong and Yuchao Dai},

year  = {2025},

date = {2025-08-13},

urldate = {2025-08-13},

journal = {arXiv preprint arXiv:2508.09525},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ren2025panosplatt3r,

title = {PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction},

author = {Jiahui Ren and Mochu Xiang and Jiajun Zhu and Yuchao Dai},

year  = {2025},

date = {2025-07-29},

urldate = {2025-07-29},

journal = {arXiv preprint arXiv:2507.21960},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{mao2025autoregressive,

title = {Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective},

author = {Yuxin Mao and Zhen Qin and Jinxing Zhou and Hui Deng and Xuyang Shen and Bin Fan and Jing Zhang and Yiran Zhong and Yuchao Dai},

year  = {2025},

date = {2025-07-02},

urldate = {2025-07-02},

journal = {arXiv preprint arXiv:2507.01652},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{mao2025contrastive,

title = {Contrastive conditional latent diffusion for audio-visual segmentation},

author = {Yuxin Mao and Jing Zhang and Mochu Xiang and Yunqiu Lv and Dong Li and Yiran Zhong and Yuchao Dai},

year  = {2025},

date = {2025-06-23},

urldate = {2025-06-23},

journal = {IEEE Transactions on Image Processing},

volume = {34},

pages = {4108 - 4119},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wang2025looprefine,

title = {LoopRefine: Deep Camera Pose Estimation With Loop Consistency},

author = {Zhiwei Wang and Hui Deng and Jiawei Shi and Mochu Xiang and Zhicheng Lu and Qi Liu and Yuchao Dai},

year  = {2025},

date = {2025-06-19},

urldate = {2025-06-19},

journal = {IEEE Robotics and Automation Letters},

volume = {10},

issue = {8},

pages = {8003 - 8010},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{li2025meeseeks,

title = {The Meeseeks Mesh: Spatially Consistent 3D Adversarial Objects for BEV Detector},

author = {Aixuan Li and Mochu Xiang and Jing Zhang and Yuchao Dai},

year  = {2025},

date = {2025-05-28},

urldate = {2025-05-28},

journal = {arXiv preprint arXiv:2505.22499},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ma2025one,

title = {One RL to See Them All: Visual Triple Unified Reinforcement Learning},

author = {Yan Ma and Linge Du and Xuyang Shen and Shaoxiang Chen and Pengfei Li and Qibing Ren and Lizhuang Ma and Yuchao Dai and Pengfei Liu and Junjie Yan},

year  = {2025},

date = {2025-05-23},

urldate = {2025-05-23},

journal = {arXiv preprint arXiv:2505.18129},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wang2025etv,

title = {ETV-MVS: Robust Visibility-Aware Multi-View Stereo with Epipolar Line-Based Transformer},

author = {Shaoqian Wang and Xiaokun Ding and Yuxin Mao and Yuchao Dai},

year  = {2025},

date = {2025-04-04},

urldate = {2025-04-04},

journal = { Big Data Mining and Analytics},

volume = {8},

issue = {3},

pages = {520 - 533},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wan2025instance,

title = {Instance-Level Moving Object Segmentation from a Single Image with Events},

author = {Zhexiong Wan and Bin Fan and Le Hui and Yuchao Dai and Gim Hee Lee},

year  = {2025},

date = {2025-02-20},

urldate = {2025-02-20},

journal = {International Journal of Computer Vision},

volume = {133},

pages = {4042–4063},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fan2024spatio,

title = {Spatio-temporal interactive learning for efficient image reconstruction of spiking cameras},

author = {Bin Fan and Jiaoyang Yin and Yuchao Dai and Chao Xu and Tiejun Huang and Boxin Shi},

year  = {2024},

date = {2024-12-16},

urldate = {2024-12-16},

booktitle = {Advances in Neural Information Processing Systems},

journal = {Advances in Neural Information Processing Systems},

volume = {37},

pages = {21401--21427},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{li2024generative,

title = {A Generative Victim Model for Segmentation},

author = {Aixuan Li and Jing Zhang and Jiawei Shi and Yiran Zhong and Yuchao Dai},

year  = {2024},

date = {2024-12-01},

urldate = {2024-12-01},

journal = {arXiv preprint arXiv:2412.07274},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{deng2024deepb,

title = {Deep Non-rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling},

author = {Hui Deng and Jiawei Shi and Zhen Qin and Yiran Zhong and Yuchao Dai},

year  = {2024},

date = {2024-12-01},

urldate = {2024-12-01},

journal = {arXiv preprint arXiv:2412.07230},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rao2024cascaded,

title = {Cascaded recurrent networks with masked representation learning for stereo matching of high-resolution satellite images},

author = {Zhibo Rao and Xing Li and Bangshu Xiong and Yuchao Dai and Zhelun Shen and Hangbiao Li and Yue Lou},

year  = {2024},

date = {2024-12-01},

urldate = {2024-12-01},

journal = {ISPRS Journal of Photogrammetry and Remote Sensing},

volume = {218},

pages = {151–165},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{zhang20243d,

title = {3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration},

author = {Liyuan Zhang and Le Hui and Qi Liu and Bo Li and Yuchao Dai},

year  = {2024},

date = {2024-11-01},

urldate = {2024-11-01},

journal = {arXiv preprint arXiv:2411.07740},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fan2024unified,

title = {Unified Video Reconstruction for Rolling Shutter and Global Shutter Cameras},

author = {Bin Fan and Zhexiong Wan and Boxin Shi and Chao Xu and Yuchao Dai},

year  = {2024},

date = {2024-10-01},

urldate = {2024-10-01},

journal = {IEEE Transactions on Image Processing},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{cao2024loflat,

title = {LoFLAT: Local Feature Matching using Focused Linear Attention Transformer},

author = {Naijian Cao and Renjie He and Yuchao Dai and Mingyi He},

year  = {2024},

date = {2024-10-01},

urldate = {2024-10-01},

journal = {arXiv preprint arXiv:2410.22710},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wang2024adaptive,

title = {Adaptive Feature Enhanced Multi-View Stereo with Epipolar Line Information Aggregation},

author = {Shaoqian Wang and Bo Li and Jian Yang and Yuchao Dai},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Robotics and Automation Letters},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{mao2024generative,

title = {Generative transformer for accurate and reliable salient object detection},

author = {Yuxin Mao and Jing Zhang and Zhexiong Wan and Xinyu Tian and Aixuan Li and Yunqiu Lv and Yuchao Dai},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Transactions on Circuits and Systems for Video Technology},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fan2024self,

title = {Self-supervised learning for rolling shutter temporal super-resolution},

author = {Bin Fan and Ying Guo and Yuchao Dai and Chao Xu and Boxin Shi},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Transactions on Circuits and Systems for Video Technology},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{deng2024deep,

title = {Deep non-rigid structure-from-motion: A sequence-to-sequence translation perspective},

author = {Hui Deng and Tong Zhang and Yuchao Dai and Jiawei Shi and Yiran Zhong and Hongdong Li},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{qin2024you,

title = {You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet},

author = {Zhen Qin and Yuxin Mao and Xuyang Shen and Dong Li and Jing Zhang and Yuchao Dai and Yiran Zhong},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {arXiv preprint arXiv:2405.21022},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wang2024efficient,

title = {Efficient Multi-view Stereo by Dynamic Cost Volume and Cross-scale Propagation},

author = {Shaoqian Wang and Bo Li and Yuchao Dai},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Transactions on Circuits and Systems for Video Technology},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{xiang2024towards,

title = {Towards a Unified Network for Robust Monocular Depth Estimation: Network Architecture, Training Strategy and Dataset},

author = {Mochu Xiang and Yuchao Dai and Feiyu Zhang and Jiawei Shi and Xinyu Tian and Zhensong Zhang},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {International Journal of Computer Vision},

volume = {132},

number = {4},

pages = {1012–1028},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lv2024weakly,

title = {Weakly-supervised contrastive learning for unsupervised object discovery},

author = {Yunqiu Lv and Jing Zhang and Nick Barnes and Yuchao Dai},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Transactions on Image Processing},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fan2024revisit,

title = {A revisit of the normalized eight-point algorithm and a self-supervised deep solution},

author = {Bin Fan and Yuchao Dai and Yongduek Seo and Mingyi He},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Visual Intelligence},

volume = {2},

number = {1},

pages = {3},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{guo2024learn,

title = {Learn to triangulate scene coordinates for visual localization},

author = {Xiang Guo and Tianrui Chen and Bo Li and Qi Liu and Huarong Jia and Yuchao Dai},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Robotics and Automation Letters},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{xiang2024measuring,

title = {Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation},

author = {Mochu Xiang and Jing Zhang and Nick Barnes and Yuchao Dai},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Transactions on Circuits and Systems for Video Technology},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fan2024learning,

title = {Learning Bilateral Cost Volume for Rolling Shutter Temporal Super-Resolution},

author = {Bin Fan and Yuchao Dai and Hongdong Li},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sun2021munet,

title = {MUNet: Motion Uncertainty-aware Semi-supervised Video Object Segmentation},

author = {Jiadai Sun and Yuxin Mao and Yuchao Dai and Yiran Zhong and Jianyuan Wang},

year  = {2023},

date = {2023-06-01},

urldate = {2021-01-01},

journal = {Pattern Recognition},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{li2023mutual,

title = {Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection},

author = {Aixuan Li and Yuxin Mao and Jing Zhang and Yuchao Dai},

year  = {2023},

date = {2023-01-01},

journal = {IEEE Transactions on Circuits and Systems for Video Technology},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{qin2023toeplitz,

title = {Toeplitz Neural Network for Sequence Modeling},

author = {Zhen Qin and Xiaodong Han and Weixuan Sun and Bowen He and Dong Li and Dongxu Li and Yuchao Dai and Lingpeng Kong and Yiran Zhong},

year  = {2023},

date = {2023-01-01},

journal = {arXiv preprint arXiv:2305.04749},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{song2023tusr,

title = {TUSR-Net: Triple Unfolding Single Image Dehazing With Self-Regularization and Dual Feature to Pixel Attention},

author = {Xibin Song and Dingfu Zhou and Wei Li and Yuchao Dai and Zhelun Shen and Liangjun Zhang and Hongdong Li},

year  = {2023},

date = {2023-01-01},

journal = {IEEE Transactions on Image Processing},

volume = {32},

pages = {1231–1244},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fan2023rolling,

title = {Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video},

author = {Bin Fan and Yuchao Dai and Hongdong Li},

year  = {2023},

date = {2023-01-01},

journal = {IEEE Transactions on Pattern Analysis & Machine Intelligence},

volume = {45},

number = {05},

pages = {6214–6230},

publisher = {IEEE Computer Society},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wang2022cu,

title = {CU-Net: LiDAR depth-only completion with coupled U-Net},

author = {Yufei Wang and Yuchao Dai and Qi Liu and Peng Yang and Jiadai Sun and Bo Li},

year  = {2022},

date = {2022-01-01},

journal = {IEEE Robotics and Automation Letters},

volume = {7},

number = {4},

pages = {11476–11483},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}