Alert button
Picture for Hongwei Qin

Hongwei Qin

Alert button

Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling

Jan 31, 2024
Xiaoyu Shi, Zhaoyang Huang, Fu-Yun Wang, Weikang Bian, Dasong Li, Yi Zhang, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin, Jifeng Dai, Hongsheng Li

Viaarxiv icon

Idempotence and Perceptual Image Compression

Jan 17, 2024
Tongda Xu, Ziran Zhu, Dailan He, Yanghao Li, Lina Guo, Yuanyuan Wang, Zhe Wang, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang

Viaarxiv icon

Unified learning-based lossy and lossless JPEG recompression

Dec 05, 2023
Jianghui Zhang, Yuanyuan Wang, Lina Guo, Jixiang Luo, Tongda Xu, Yan Wang, Zhi Wang, Hongwei Qin

Viaarxiv icon

Efficient Learned Lossless JPEG Recompression

Aug 25, 2023
Lina Guo, Yuanyuan Wang, Tongda Xu, Jixiang Luo, Dailan He, Zhenjun Ji, Shanshan Wang, Yang Wang, Hongwei Qin

Figure 1 for Efficient Learned Lossless JPEG Recompression
Figure 2 for Efficient Learned Lossless JPEG Recompression
Figure 3 for Efficient Learned Lossless JPEG Recompression
Figure 4 for Efficient Learned Lossless JPEG Recompression
Viaarxiv icon

Conditional Perceptual Quality Preserving Image Compression

Aug 16, 2023
Tongda Xu, Qian Zhang, Yanghao Li, Dailan He, Zhe Wang, Yuanyuan Wang, Hongwei Qin, Yan Wang, Jingjing Liu, Ya-Qin Zhang

Figure 1 for Conditional Perceptual Quality Preserving Image Compression
Figure 2 for Conditional Perceptual Quality Preserving Image Compression
Figure 3 for Conditional Perceptual Quality Preserving Image Compression
Figure 4 for Conditional Perceptual Quality Preserving Image Compression
Viaarxiv icon

FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow

Jun 08, 2023
Zhaoyang Huang, Xiaoyu Shi, Chao Zhang, Qiang Wang, Yijin Li, Hongwei Qin, Jifeng Dai, Xiaogang Wang, Hongsheng Li

Figure 1 for FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow
Figure 2 for FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow
Figure 3 for FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow
Figure 4 for FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow
Viaarxiv icon

VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

Mar 17, 2023
Xiaoyu Shi, Zhaoyang Huang, Weikang Bian, Dasong Li, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin, Jifeng Dai, Hongsheng Li

Figure 1 for VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
Figure 2 for VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
Figure 3 for VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
Figure 4 for VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
Viaarxiv icon

KBNet: Kernel Basis Network for Image Restoration

Mar 06, 2023
Yi Zhang, Dasong Li, Xiaoyu Shi, Dailan He, Kangning Song, Xiaogang Wang, Hongwei Qin, Hongsheng Li

Figure 1 for KBNet: Kernel Basis Network for Image Restoration
Figure 2 for KBNet: Kernel Basis Network for Image Restoration
Figure 3 for KBNet: Kernel Basis Network for Image Restoration
Figure 4 for KBNet: Kernel Basis Network for Image Restoration
Viaarxiv icon

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

Mar 02, 2023
Xiaoyu Shi, Zhaoyang Huang, Dasong Li, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin, Jifeng Dai, Hongsheng Li

Figure 1 for FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
Figure 2 for FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
Figure 3 for FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
Figure 4 for FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
Viaarxiv icon