VIP-P5: 3D and multi-modal imaging
Thu, 11 Sep, 15:30 - 17:10 Italy Time (UTC +2)
Location: Poster Area E
Session Type: Poster
Session Co-Chairs: Gerasimos Potamianos, Athena Research Center and Nikos Nikolaidis, Aristotle University of Thessaloniki
Track: VIP - Visual Information Processing

VIP-P5.1: SAGE: Semantic-Driven Adaptive Gaussian Splatting in Extended Reality
Chiara Schiavo, Elena Camuffo, Leonardo Badia, Simone Milani, University of Padova, Italy

VIP-P5.2: BOGAUSS: BETTER OPTIMIZED GAUSSIAN SPLATTING
Stéphane Pateux, Matthieu Gendrin, Orange, France; Luce Morin, Univ Rennes, France; Théo Ladune, Orange, France; Xiaoran Jiang, Univ Rennes, France

VIP-P5.3: MODALITY TRANSLATION AND REGISTRATION OF MR AND ULTRASOUND IMAGES USING DIFFUSION MODELS
xudong ma, Nantheera Anantrasirichai, university of bristol, United Kingdom; Stefanos Bolomytis, Southmead Hospital, North Bristol NHS Trust, United Kingdom; Alin Achim, university of bristol, United Kingdom

VIP-P5.4: CONFORMER-BASED MULTI-MODAL LEARNING FOR CUED SPEECH RECOGNITION FROM VIDEOS
Katerina Papadimitriou, Gerasimos Potamianos, Athena Research Center, Greece

VIP-P5.5: CROSS-MODAL SELF-SUPERVISED ADVERSARIAL LEARNING FOR MA-XRF SUPER-RESOLUTION
Herman Verinaz-Jadan, Escuela Superior Politecnica del Litoral, Ecuador; Su Yan, Imperial College London, United Kingdom; Catherine Higgitt, The National Gallery, United Kingdom; Pier Luigi Dragotti, Imperial College London, United Kingdom

VIP-P5.6: GENERATION OF ANNOTATED DATA FOR HUMAN-CENTRIC COMPUTER VISION TASKS USING AUGMENTED REALITY
Alexandros Vasileiadis, Nikos Nikolaidis, Aristotle University of Thessaloniki, Greece

VIP-P5.7: Rate Control for Point Cloud Compression with Adaptive Updates to the Rate-Quantization Model
Yohei Hanaoka, Kohei Matsuzaki, Kyohei Unno, Keisuke Nonaka, KDDI Research, Inc., Japan

VIP-P5.8: Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Space
Luc Vedrenne, Sylvain Faisan, Denis Fortun, CNRS, University of Strasbourg, France