IVMSP-P20.7

Exploiting spatial attention mechanism for improved depth completion and feature fusion in novel view synthesis

Anh Minh Truong, Wilfried Philips, Peter Veelaert, Ghent University Ringgold standard institution - Telecommunications and Information Processing Gent Belgium

Session:
IVMSP-P20: 3D image and video processing and analysis II Poster

Track:
Image, Video, and Multidimensional Signal Processing

Location:
Poster Zone 2C
Poster Board PZ-2C.7

Presentation Time:
Fri, 19 Apr, 08:20 - 10:20 (UTC +9)

Session Chair:
Haonan Cheng, Communication University of China, China
Presentation
Discussion
Resources
No resources available.
Session IVMSP-P20
IVMSP-P20.1: TOWARDS OMNISCIENT FEATURE ALIGNMENT FOR VIDEO RESCALING
Guanchen Ding, Chang Wen Chen, The Hong Kong Polytechnic University, Hong Kong
IVMSP-P20.2: ANOMALY-AWARE SEMANTIC SELF-ALIGNMENT FRAMEWORK FOR VIDEO-BASED PERSON RE-IDENTIFICATION
Zhidan Ran, Xiaobo Lu, Wei Liu, Southeast University, China
IVMSP-P20.3: SKETCH-BASED 3D SHAPE RETRIEVAL WITH MULTI-VIEW FUSION TRANSFORMER
Cunjuan Zhu, Dongdong Cui, Qi Jia, Weimin Wang, Yu Liu, Dalian University of Technology, China; Michael S. Lew, Leiden University, Netherlands
IVMSP-P20.4: PERCEPTUAL QUALITY EVALUATION FOR FASTER PLAYBACK VIDEOS
Jiarun Song, Shengnan Wang, Fuzheng Yang, Xidian University, China
IVMSP-P20.5: MMAFLOW: MATCHING-GUIDED MOTION AGGREGATION FOR OPTICAL FLOW ESTIMATION
Yongpeng Chang, Zhejiang University, China; Guangchun Gao, Hangzhou City University, China
IVMSP-P20.6: EXPLORING PHONETIC CONTEXT-AWARE LIP-SYNC FOR TALKING FACE GENERATION
Se Jin Park, Minsu Kim, Jeongsoo Choi, Yong Man Ro, KAIST, Korea, Republic of
IVMSP-P20.7: Exploiting spatial attention mechanism for improved depth completion and feature fusion in novel view synthesis
Anh Minh Truong, Wilfried Philips, Peter Veelaert, Ghent University Ringgold standard institution - Telecommunications and Information Processing Gent Belgium
IVMSP-P20.8: MuSR: Multi-Scale 3D Scenes Reconstruction based on Monocular Video
Han Gao, Hao Wu, Peiwen Dong, Yixin Xu, Fengyuan Xu, Sheng Zhong, Nanjing University, China
IVMSP-P20.9: One-stage Deep Stereo Network
ziming liu, ezio malis, philippe martinet, INRIA, France
IVMSP-P20.10: REFINING 3D HUMAN MESH VIA MODEL-FREE OFFSETS ESTIMATION
Youze Xue, Tsinghua University, China; Jiansheng Chen, University of Science and Technology Beijing, China; Hongbing Ma, Tsinghua University, China; Huimin Ma, University of Science and Technology Beijing, China
IVMSP-P20.11: DI-MVS: LEARNING EFFICIENT MULTI-VIEW STEREO WITH DEPTH-AWARE ITERATIONS
Jianfei Jiang, Mingwei Cao, Anhui University, China; Jun Yi, Hefei University of Technology, China; Chenglong Li, Anhui University, China
IVMSP-P20.12: TransCycle: A Data Augmentation Method For 3D Human Pose Estimation
Bowei Zhang, Rongting Xu, Peng Cui, Guizhou University of Finance and Economic, China
Contacts