Special Sessions

SS-1: Generative AI for Image/Video Coding

[10:30–12:00] Conference Room 1

Chair: Xin Jin (Eastern Institute of Technology)

[P-ID 027] Lossy Coding for Spatially Adaptive Conditioning in Semantic Image Communication

Cem Eteke (Technical University of Munich)*; Alexander Griessel (Technical University of Munich); Wolfgang Kellerer (Technical University of Munich); Eckehard Steinbach (TUM)

[P-ID 122] Perceptual Image Compression With Conditional Diffusion Transformers

Rui Mao (University of Science and Technology of China); Xinmin Feng (University of Science and Technology of China); Changsheng Gao (University of Science and Technology of China); Li Li (University of Science and Technology of China); Dong Liu (University of Science and Technology of China); Xiaoyan Sun (University of Science and Technology of China)*

[P-ID 152] Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs

Jinming Liu (Shanghai Jiao Tong University)*; Yuntao Wei (University of Science and Technology of China); Junyan Lin (Ocean University of China); Shengyang Zhao (Ningbo Institute of Digital Twin); Heming Sun (Yokohama National University); Zhibo Chen (University of Science and Technology of China); Wenjun Zeng (Eastern Institute of Technology, Ningbo); Xin Jin (Eastern Institute of Technology, Ningbo, China)

SS-2: Lenslet Video Coding and Processing

[14:00–15:30] Masaru Ibuka Auditorium

Chair: Xin Jin (Shenzhen International Graduate School, Tsinghua University), Mehrdad Teratani (Aichi University of Technology)

[P-ID 053] TSARN: A Joint Temporal-Spatial-Angular Reconstruction Network for Light Field Lenslet Video Compression (Best Paper Candidate)

Huan Li (Shanghai University); Xinpeng Huang (Shanghai University)*; Yongjie Lu (Shanghai University); Ping An (Shanghai University)

[P-ID 133] Advancements in Lenslet Video Coding: Insights from MPEG LVC

Xin Jin (Tsinghua University)*; Mehrdad Teratani (Université Libre de Bruxelles); Byeungwoo Jeon (Sungkyunkwan University); Toshiaki Fujii (Nagoya Univ.); Ruibo Zhao (Tsinghua University); Eline Soetens (Université Libre de Bruxelles); Yuqing Yang (Tsinghua University)

[P-ID 192] Codec-agnostic Lenslet Video Coding with Smoothing Transform

Eline Soetens (Université Libre de Bruxelles)*; Gauthier Lafruit (ULB-LISA); Mehrdad Teratani (Université Libre de Bruxelles)

[P-ID 209] Enhancing Intra Block Copy Prediction for Plenoptic 2.0 Video Coding under Macropixel Constraints

Vinh Van Duong (Sungkyunkwan University); Thuc Nguyen Huu (SKKU); Jong Hoon Yim (Sungkyunkwan University); Byeungwoo Jeon (Sungkyunkwan University)*

[P-ID 267] Multi-view Rendering for Plenoptic 2.0 Videos with Multi-reference Patch Size Estimation

Zhuo Tan (Tsinghua Shenzhen International Graduate School); Xin Jin (Tsinghua University)*

SS-3: Recent Advancements in Versatile Supplemental Enhancement Information (VSEI)

[13:30–15:00] Masaru Ibuka Auditorium

Chair: Jill Boyce (Nokia), Teruhiko Suzuki (Sony)

[P-ID 196] Signaling of object masks with the assistance of the object mask information SEI message

Jie Chen (Alibaba)*; Zixiang Zhang (Alibaba); Yan Ye (Alibaba Inc.); Shurun Wang (Alibaba Group)

[P-ID 205] The source picture timing SEI message in the VSEI standard

Sean McCarthy (Dolby)*; Gary J. Sullivan (Dolby); Peng Yin (Dolby)

[P-ID 077] Film Grain Regions characteristics SEI message

Edouard Francois (InterDigital)*; Philippe de Lagrange (InterDigital); Franck Galpin (InterDigital); Gilles Teniou (Tencent); Stephan Wenger (Tencent)

[P-ID 074] Encoder Optimization Information SEI Message for Identifying Optimization Objectives and Methods

ChulKeun Kim (LG electronics)*; Hendry Tan (LG electronics); Jaehyun Lim (LG electronics); Seung-Hwan Kim (LG Electronics)

[P-ID 225] Packed Regions Information SEI Message

Jill Boyce (Nokia)*; Miska Hannuksela (Nokia Technologies); Honglei Zhang (Nokia Technologies); Antti Hallapuro (Nokia)

SS-4: Implicit and Explicit Neural Representations for nD Video Compression

[10:30–12:00] Masaru Ibuka Auditorium

Chair: Yiyi Liao (Zhejiang University)

[P-ID 219] PET-NeRV: Bridging Generalized Video Codec and Content-Specific Neural Representation

Hao Li (Zhejiang Univerisity); Lu Yu (Zhejiang University); Yiyi Liao (Zhejiang University)*

[P-ID 274] A Practical Approach to Depth-Aware Augmentation for Neural Radiance Fields

Hamed Razavi Khosroshahi (Université libre de Bruxelles (ULB))*; Jaime Sancho (Universidad Politécnica de Madrid); Daniele Bonatto (Université Libre de Bruxelles); Sarah Fachada (Université Libre de Bruxelles); Gun Bang (ETRI); Gauthier Lafruit (ULB-LISA); Eduardo Juarez (Universidad Politécnica de Madrid); Mehrdad Teratani (Université Libre de Bruxelles)

[P-ID 168] Dynamic Volumetric Video Coding with Tensor Decomposition

Juyeon Shin (Ewha W University); Yeoneui Kim (Ewha Womans University); Gun Bang (ETRI); Jewon Kang (Ewha Womans University)*

[P-ID 292] Compressing 3D Gaussian Splatting via a Generalizable Neural Coder

Junteng Zhang (Nanjing University)*; Tong Chen (Nanjing University); Hao Zhu (Nanjing University); Dong Wang (Guangdong OPPO Mobile Telecommunications Corp., Ltd. ); Dandan Ding (Hangzhou Normal University); Zhan Ma (Nanjing University)

SS-5: Emerging Trends in Learning-based Image/Video Coding and Perceptual Quality Assessment

[13:30–15:00] Masaru Ibuka Auditorium

Chair: Yiyi Liao (Zhejiang University)

[P-ID 069] NeRV++: An Enhanced Implicit Neural Video Representation

Ahmed Ghorbel (Ecole polytechnique)*; Wassim Hamidouche (INSA Rennes); Luce Morin (INSA Rennes)

[P-ID 271] Improving Reconstruction Fidelity in Generative Face Video Coding using High Frequency Shuttling

Goluck Konuko (L2S - CentraleSupélec, Université Paris Saclay)*; Giuseppe Valenzise (CNRS, CentraleSupelec); Anthony TRIOUX (Xidian University, School of Telecommunications Engineering, Xi'an China)

[P-ID 273] Characterizing the geometric complexity of G-PCC compressed point clouds

Annalisa Gallina (Università degli Studi di Padova); Hadi Amirpour (University of Klagenfurt); Sara Baldoni (University of Padova)*; Giuseppe Valenzise (CNRS); Federica Battisti (University of Padova)

[P-ID 049] ReLI-QA: A Multidimensional Quality Assessment Dataset for Relighted Human Heads

Yingjie Zhou (Shanghai Jiao Tong University)*; Zicheng Zhang (Shanghai Jiaotong university); Farong Wen (Shanghai Jiaotong university); Jun Jia (Shanghai Jiao Tong University); Xiongkuo Min (Shanghai Jiao Tong University); Jia Wang (Shanghai Jiao Tong University); Guangtao Zhai (Shanghai Jiao Tong University)

[P-ID 187] Quantizing Neural Networks with Knowledge Distillation for Efficient Video Quality Assessment (Best Paper Candidate)