TU2.L6.5
Bits-to-Photon: End-to-End Learned Scalable Point Cloud Compression for Direct Rendering
Yueyu Hu, Ran Gong, Yao Wang, New York University, United States
Session:
TU2.L6: Emerging Immersive Video Coding Lecture
Track:
Special Sessions
Location:
Dena'ina: Tubughnenq 4
Presentation Time:
Tue, 16 Sep, 11:00 - 11:15 Anchorage Time (UTC -8)
Session Co-Chairs:
Dong Tian, InterDigital and Li Zhang, Bytedance Inc.
Session TU2.L6
TU2.L6.1: RATE-DISTORTION OPTIMIZED CHROMA QUANTIZATION FOR POINT CLOUD COMPRESSION
Bharath Vishwanath, Yingzhan Xu, Kai Zhang, Li Zhang, ByteDance Inc, United States
TU2.L6.2: GEOMETRY REGULARIZED POINT CLOUD AUTOENCODER
Ritwik Sadhu, Jiahao Pang, Dong Tian, InterDigital, United States
TU2.L6.3: JOINT GEOMETRY-ATTRIBUTE POINT CLOUD COMPRESSION WITH SPATIAL CONTEXT MINING AND DUAL-CLASS ATTRIBUTE LOSS
Yangzhi Ma, Bojun Liu, Li Li, Dong Liu, University of Science and Technology of China, China; Zhu Li, University of Missouri, Kansas City, United States
TU2.L6.4: LIFT-PCAC: LIFTING BASED POINT CLOUD ATTRIBUTE COMPRESSION
Rodrigo Borba Pinheiro, Jean-Eudes Marvie, InterDigital, Inc., France; Giuseppe Valenzise, Frédéric Dufaux, Université Paris-Saclay, CNRS, CentraleSupélec, L2S, France
TU2.L6.5: Bits-to-Photon: End-to-End Learned Scalable Point Cloud Compression for Direct Rendering
Yueyu Hu, Ran Gong, Yao Wang, New York University, United States
TU2.L6.6: CTU-LEVEL RATE CONTROL WITH λ OPTIMIZATION BASED ON VISUAL GAZE MECHANISM FOR 360-DEGREE VERSATILE VIDEO CODING
Zeming Zhao, Sichuan University, China; Meng Wang, Lingnan University, China; Xiangjie Sui, City University of Macau, China; Xiaohai He, Sichuan University, China; Shiqi Wang, City University of Hong Kong, China
Contacts