The conference Program includes accepted papers and presentations that will appear :

  1. In the Visual Computer Journal as a special issue at the same time of the conference
  2. In the LNCS Proceedings Book, or as special issues in the Journal CAVW, or in the Journal VRIH in the autumn 2024

Two workshops will take place on the first day.

Conference schedule (CET time)

Monday, July 1
CGI Workshops Day

First Parallel session

MIRALab Workshop

Auditorium

Second Parallel Session

ENGAGE workshop

Room: H8-01-D

09:00-09:20

Opening Remarks and Welcome by Prof. Nadia Thalmann, MIRALab, Université de Genève


09:00-09:30

Keynote Speaker 1:

Zhaoyuan Yu, (Nanjing Normal University, China). Geometric Algebra: a unifying language for Geographic Information Systems in the era of big data and AI.(ZOOM)

09:20-10:40

MIRALab Workshop/session 1

09:30-10:40

Engage/session 1

  • 9:20 - 9:40: Dr. Dimitris Protopsaltou, The Stavros Niarchos Foundation Cultural Center (SNFCC), a symbol of a new era in Greece Culture.

  • 9:40 - 10:00: Dr. Caecilia Charbonnier, Artanim / Dreamscape Immersive, Technics and Challenges in Creating Highly Immersive Experiences in Free-Roam Location-Based VR.

  • 10:00 - 10:20: Prof. Jinman Kim, The University of Sydney, RibMR – A Mixed
    Reality System for Rib Fracture Localization in Surgical Stabilization of Rib Fractures.

  • 10:20 - 10:40: Prof. George Papagiannakis, University of Crete, FORTH-ICS,
    ORamaVR, Journey Through the Vertex of Impactful Innovation: From Computer Graphics frameworks to Geometric Algebra and Computational Medical Extended Reality.

  • Yadi Huang et al (Nanjing Normal University, Nanjing, China): A Geometric Algebra-based machine learning method for Typhoon intensity forecasting.(ZOOM)

  • Paul Zikas (presenter on behalf Manos Kamarianakis et al), (University of Crete, Heraklion, Greece): GA-Unity: A Production-Ready Unity Package for Seamless Integration of Geometric Algebra in Networked Collaborative Applications.

  • Ed Saribatir, (School of Mathematical and Physical Sciences University of Technology, Sydney, Australia). Benchmarks of a Geometric Algebra Algorithm Executed on the CPU and SIMD Architecture of Ten Devices.(ZOOM)

  • Clément Chomicki et al, (LIGM, Université Gustave Eiffel, Paris, CNRS). Pencils of CGA for Voronoi and Power Diagram.

10:40-11:10

COFFEE BREAK

11:10-12:30

MIRALab Workshop /session 2

11:10-11:40

Keynote Speaker 2:

George Papagiannakis, 

(Computer Science department of the University of Crete, Greece and Research Fellow at FORTH-ICS, where he leads the Computer Graphics Group, Co-founder of ORamaVR, Geneva, Switzerland).

Harnessing Geometric Algebra for Impactful Computer Graphics in Extended Reality Applications.

  • 11:10 - 11:30: Prof. WonSook Lee, School of EECS, University of Ottawa. GAN and Diffusion based 3D Face Reconstruction from a Front View.

  • 11:30 - 11:50: Dr. Arjan Egges, ArjanCodes. How to Use Video to Dramatically
    Increase Your Impact.

  • 11:50 - 12:10: Prof. Igor Pandžić. University of Zagreb Faculty of Electrical
    Engineering and Computing, Faces, Cars, and Beauty.

  • 12:10 - 12:30: Prof. Chris Joslin, Carleton University, Ottawa. Facial Motion Capture, the Promise, and the Reality.

11:40-12:30

Engage/session 2

  • Eckhard Hitzer, (International Christian University, Tokyo, Japan). Properties of the Geometric Product of Two Oriented Points in Conformal Geometric Algebra.

  • Ekaterina Filimoshina, (HSE University, Moscow, Russia). Generalized Degenerate Clifford and Lipschitz Groups.(ZOOM)

  • Sven Buchholz, (Datenmanagement und Data Mining, Fachbereich Informatik und Medien, TH Brandenburg, Brandenburg, Germany).  SOMs as projector maps from Geometric Algebra Neural Layers.

12:30-13:30

LUNCH BREAK

13:30-15:10

MIRALab Workshop /session 3

13:30-15:10

Keynote Speaker 3:

Pim de Haan, (Research Associate at Qualcomm AI Research, The Netherlands). Machine learning for science with the Geometric Algebra Transformer.(ZOOM)

  • 13:30 - 13:50: Dr. Lydia Yahia Cherif, CNRS-ICM-Académie des Technologies.
    Computational Modeling and Multimodal Neuroimaging Approaches to Investigate Brain Dynamics.

  • 13:50 - 14:10: Dr. Matthias Becker, German Center for Neurodegenerative Diseases
    (DZNE)- Bonn, Germany. Collaboration in Alzheimer’s Research: From Synthetic Data to Swarm Learning.

  • 14:10 - 14:30: Prof. Jérôme Schmid, Geneva School of Health Sciences – HES-SO.
    Make me smarter: when knowledge improves computer-assisted medical image analysis.

  • 14:30 - 14:50: Prof. Christiane Luible, University of Arts Linz, Fashion & Technology.
    The new age of digital and sustainable Fashion.

  • 14:50 - 15:10: Dr. Hyewon Seo, CNRS-University of Strasbourg. Inverse Garment and Pattern Modeling with a Differentiable Simulator.

14:00-14:50

Engage/session3

  • Dmitry Shirokov, (HSE University, Moscow, Russia). On SU(3) in Ternary Clifford Algebra.(ZOOM)

  • Patrick R. Girard et al, (INSA-LYON, Universite Claude Bernard Lyon 1, CNRS, Inserm, CREATIS UMR 5220, U1294, F-69621 Lyon, France). Hyperquaternionic Unitary Symplectic Groups: A Unifying Tool for Physics.

  • Sofia Rumyantseva, (HSE University, Moscow, Russia). On Multidimensional Dirac--Hestenes Equation in Geometric Algebra.

14:50-15:10

Software demonstration by Wilder Lopes and Conclusion

15:10-15:40

COFFEE BREAK

15:40-17:00

MIRALab Workshop /session 4

15:40-17:40

Medical Session

  • 15:40 - 16:00: Dr. Mustafa Kasap, Principal AI Architect. The New Era of Creativity: Unpacking the Latest in Generative AI.

  • 16:00 - 16:20: Prof. Frederic Cordier, University of Haute-Alsace. Sketch-based Modeling.

  • 16:20 - 16:40: Prof. Young-Min Kang, Tongmyong University. Arbitrary-order
    Reachability Computation for Large Graph Structures.

  • 16:40 - 17:00: Dr. Yvain Tisserand, Swiss Center for Affective Sciences - University of
    Geneva. Virtual Humans and Virtual Environments in Affective Science Research.

  • Adrian Vulpe-Grigorasi, Benedikt Gollan, and Vanessa Leung: Assessing Cognitive Load in Distraction and Task Switching: Implications for Developing Realistic Clinical XR Training.

  • George Papagiannakis, Walter Greenleaf, Michael Cole, Mark Zhang, Rabi Datta, Mathias Delahaye, Eleni Grigoriou, Manos Kamarianakis, Antonis Protopsaltis, Philippe Bijlenga, Nadia Magnetat Thalmann, Eleftherios Tsiridis, Eustathios Kenanidis, Kyriakos Vamvakidis, Ioannis Koutelidakis and Oliver Kannape. A Computational Medical XR Discipline

Panel on VR & Medicine

Chair: Oliver Kannape, HUG, Geneva

Panelists:

Vanessa Leung, St Poelten University of Applied Science, Austria.

Caecilia Charbonnier, Artanim / Dreamscape Immersive.

George Pagagiannakis, ORamaVR, Switzerland.

17:00-17:40

MIRALab Workshop /session 5

Short talks

  • 17:00 - 17:10: Dr. Neeharika Adabala, Independent researcher/software developer.
    Knowledge Companion – a creator’s tool to navigate information.

  • 17:10 - 17:20: Dr. Ignasi Giró, Airbus – Toulouse.Successfully failing embracing failure to design meaningful services and products.

  • 17:20 - 17:30: Prof. Prem Kumar Kalra, Indian Institute of Technology Delhi. An Overview of Research in Visual Computing Post MIRALab. (ONLINE)

  • 17:30 - 17:40: Dr. Thomas Di Giacomo, SUSE. From MIRALab and CG to Infrastructure Software.

17:40

Closing Remarks

18:00 - 19:30

CGI 2024 WELCOME COCKTAIL

Tuesday, July 2

CGI Conference Day 2

09:00-09:15

Welcome to CGI2024

by

Prof. Nadia Magnenat Thalmann, President of CGS, CGI2024 Conference co-chair

Prof. Jinman Kim, Vice-President of CGS, CGI Conference co-chair

Prof. Jian Jun Zhang, CGS board, Member of the CGI2024 Awards Committee

09:15-10:00

CGI Keynote  1

Prof. Jinman Kim - the University of Sydney. 

Multi-modal Learning for Biomedical Image Analysis and Visualisation 


Chair: Nadia Thalmann, MIRALab, University of Geneva

10:00-10:30

COFFEE BREAK

First Parallel session

Room: Auditorium

Second Parallel session

Room: H8-01-D

Third Parallel Session

Room: H4-02-A

10:30-11:50

TVC 1 Deep Learning for Graphics 1

Chair: Marina Gavrilova, U. of Calgary

LNCS 11

Chair: Daniel Thalmann, EPFL

  • Xiaonan He, Yukun Xia, Yuansong Qiao, Brian Lee and Yuhang Ye, Semantic Guidance Incremental Network for Efficiency Video Super Resolution. (ZOOM)

  • Xiaoxian Tian, Chongke Bi, Ce Yu and Jun Han, EasyRP-R-CNN: A Fast Cyclone Detection Model. (ZOOM)

  • Pengjie Wang, Kang Yang, Chengzhi Yuan, Houjie Li, Wen Tang and Xiaosong Yang, Few-Shot Anime Pose Transfer.

  • Ekin Marlali and Selim Balcisoy, Automated Inpainting of Tex Willer Comics: Adapting Manga Techniques for Western Comic Transformation.

  • Yicheng Zhao, Jiacheng Lu, Bo Li and Hui Ding, Edge Enhancement and Dual UNet Fusion Based Gan for Structure Preserving Stain Normalization.(ZOOM)

  • Longfa Liu, Kexin Gao, Chuang Li, Imad Rida, Shaohua Teng and Lunke Fei, Semantic Cross-Self-Reconstruction with Graph Convolutional Network for Zero-Shot Cross-Modal Retrieval.(ZOOM)

  • Dezhi Liu, Weibing Wan, Zhijun Fang and Xiuyuan Zheng, UrgRF:Radiance Field Reconstruction Guided by Low-Resolution Grids.(ZOOM)

  • Philipp Drescher, Irena Ruprecht and Volker Settgast, Combining Stable Diffusion and Object Detection for Semi-Automatic Environment Decoration.

11:50-12:50

TVC 2 Terrain and Texture

Chair: Marina Gavrilova, U. of Calgary

LNCS 12

Chair: Daniel Thalmann, EPFL

  • Marc Hartley, Nicolas Mellado, Christophe Fiorio and Noura Faraj, Flexible Terrain Erosion Compatible with Multiple Representations.

  • Toshiki Kanai, Yuki Endo and Yoshihiro Kanamori, Seasonal Terrain Texture Synthesis via Koppen Periodic Conditioning.

  • Eduardo Alvarado, Oscar Argudo, Damien Rohmer, Marie-Paule Cani and Nuria Pelechano, TRAIL: Simulating the Impact of Human Locomotion on Natural Landscapes.(ZOOM)

  • Hanchen Yu, Mingwei He, Feng Yu, Li Liu and Minghua Jiang, Smart Clothing System for Arrhythmia Detection based on Digital Twin Technology.(ZOOM)

  • Hoijoon Jung, Younhyun Jung, Michael Fulham and Jinman Kim, Mixed reality hologram slicer (mxdR-HS): a markerless tangible user interface for interactive holographic medical volume visualization.(ZOOM)

12:50-13:30

LUNCH BREAK

First Parallel session

Room: Auditorium

Second Parallel session

Room: H8-01-D

Third Parallel session

Room: H4-02-A

13:50-15:10

TVC 3 VR/AR

Chair: Jian Zhang, Bournemouth University

LNCS 13

Chair: Ping Li, PolyU, Hongkong

  • Tolga Capin, Berkay Terzioğlu and Ufuk Çelikcan, Gaze-Contingent Adaptation of VR Stereo Parameters for Cybersickness Prevention.

  • Conrado Jr. Ruiz, Claudia Serrano, Òscar de Jesús, Alejandro González, Pau Nonell, Arnau Metaute and David Miralles, Bridging Realities: Training visuo-haptic object recognition models for robots using 3D virtual simulations.

  • Yu Wei Tan, Siang Ern Low, Jonas Chow, Javon Teo and Dr. Bhojan Anand, DHR+S: Distributed Hybrid Rendering with Realistic Real-time Shadows for Interactive Thin Client Metaverse and Game Applications.

  • Anqi Chen, Ming Li and Yang Gao, MEM-Box: VR Sandbox for Adaptive Working Memory Evaluation and Training Using Physiological Signals. 

  • Byungju Chae and Jaeho Im, Real-ESRGAN based EXR Upscale for VFX Pipeline.

  • Jixing Yang, Bo Yang, Xincheng Hu and Guang Zhou, Temporal Fusion Network for Continuous Sign Language Recognition.(ZOOM)

  • Yan Zhou, De Wang Ye, Ye Wen Xu, Yue Xia Zhou, Xiang Yu Liu, Zhao Jian Lin and Hao Tian Lei, Rectified Flow for Efficient Automatic Implant Generation.(ZOOM)

  • John Li, Zhicheng Liu, Feng Tian and Jinyuan Jia, Web3D-Based Lightweight Simulation for Mass Evacuation at Transportation Hubs.(ZOOM)

15:10-15:40

COFFEE BREAK

Room: Auditorium

Room: H8-01-D

Room: H4-02-A

15:40-17:00

TVC 4 Animation and Simulation

Chair: Jian Zhang, Bournemouth University

CAVW 1

Chair: Ping Li, PolyU, Hongkong

LNCS 14

Chair: Paul Zikas, ORamaVR

  • Hui Fang, Yin Ma, Zeyu Tian and Dongdong Weng, ManTalk: Manipulable Talking Head Generation from Single Image in the Wild.(ZOOM)

  • Saba Khan and Zhigang Deng, Agent-based Crowd Simulation: An In-depth Survey of Determining Factors.(ZOOM)

  • Irena Ruprecht, Florian Michelic, Eva Eggeling and Reinhold Preiner, Adaptive Movement Behavior for Real-Time Crowd Simulation.

  • Soma Yokota and Issei Fujishiro, Visual simulation of opal using bond percolation through the weighted Voronoi diagram and the Ewald construction.

  • Liu Jingyao, Tianlu Mao and Zhaoqi Wang, VTSIM : Attention-based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation.(ZOOM)

  • Jackson Yang, Xiaoping Che, Chenxin Qu, Xiaofei Di and Haiming Liu,  Enhancing Virtual Reality Exposure Therapy: Optimizing Treatment Outcomes for Agoraphobia Through Advanced Simulation and Comparative Analysis.(ZOOM)

  • Yiwen Ma, Tingting Liu and Zhen Liu, Diverse Motions and Responses in Crowd Simulation.(ZOOM)

  • Wataru Umezawa and Tomohiko Mukai, Training Climbing Roses By Constrained Graph Search.

  • Hui Ding, Chong Liu, Yawei Zhang, Bo Li, Yuhan Huang, Jiacheng Lu and Kaiwen Wang, CF-Net: A Hybrid CNN-Random Forest Network for Depression Classification in Brain MRI.(ZOOM)

  • Jiaxin Peng, Tao Li and Jie Liu, YFLM: An Improved Levenberg-Marquardt Algorithm for Global Bundle Adjustment.(ZOOM)

  • Yuyu Jin, Zhiyong Xiao, Jiaqi Yuan, Mingwei He, Li Liu, Feng Yu and Minghua Jiang, MFENet: Multi-Scale and Local Frequency Enhancement Network for Skin Lesion Classification.(ZOOM)

  • Dongjin Huang, Yilin Li, Jiantao Qu, Shiyu Zhang and Qian Wang, YOLOv8-MGH:Dense crowd object detection.(ZOOM)

Wednesday, July 3

CGI Conference Day 3

09:00-09:15

Welcome to CGI

09:15-10:00

CGI Keynote 2 (Online)

Prof. Bin SHENG – Shanghai Jiao Tong University

REVERIE: An ensemble-based VR sports system employing deep reinforcement learning to combat adolescent obesity

Chair: Daniel Thalmann, EPFL

10:00-10:30

COFFEE BREAK

First Parallel Session

Room: Auditorium

Second Parallel Session

Room: H8-01-D

Third Parallel session

Room: H4-02-A

10:30-11:50

CAVW 2

Chair: Daniel Thalmann, EPFL

TVC 5 Image Analysis and Processing

Chair: Paul Zika, ORamaVR

LNCS 15

Chair: Thiago Freitas, MIRALab, UNIGE

  • Zhiyong Xiao, Yukun Chen, Xinlei Zhou, Mingwei He, Li Liu, Feng Yu and Minghua Jiang. Human Action Recognition in Immersive Virtual Reality Based on Multi-scale Spatio-Temporal Attention Network.(ZOOM)

  • Changan Zhu and Chris Joslin. A Facial Motion Retargeting Pipeline for Appearance Agnostic 3D Characters.

  • Hangyeol Kang, Maher Ben Moussa and Nadia Magnenat Thalmann. Nadine: An LLM-driven Intelligent Social Robot with Affective Capabilities and Human-like Memory.

  • George Kokiadis, Antonis Protopsaltis, Michalis Morfiadakis, Nick Lydatakis and George Papagiannakis. Decoupled Edge Physics algorithms for collaborative XR simulations.

  • Haiqiang Zhou, Wangkang Huang, Zhenyang Zhu, Xiaodiao Chen, Kentaro Go and Xiaoyang Mao. Fast Image Recoloring for Red-Green Anomalous Trichromacy with Contrast Enhancement and Naturalness Preservation.

  • Fariha Iffath and Marina L Gavrilova. ARF-Net: A Multi-modal Aesthetic Attention-based Fusion.

  • Yijia Zeng and Chi Man Pun. Frequency-constrained Transferable Adversarial Attack on Image Manipulation Detection and Localization.(ZOOM)

  • Tristan Wirth, Arne Rak, Max von Buelow, Volker Knauthe, Arjan Kuijper and Dieter Fellner. NeRF-FF: A Plug-In Method to Mitigate Defocus-Blur for Run-Time Optimized Neural Radiance Fields.

  • Luciano Arnaldo Romero Calla and Renato Pajarola. Interactive Ray Tracing of 3D Indoor Scanned Point Clouds.

  • Yongqi Huang, Feng Liu and Aimin Zhou. GSMC: A Global-local Scalable Multi-task Contrastive Learning Framework.(ZOOM)

  • Kevin Napoli, Keith Bugeja, Sandro Spina and Mark Magro. Spectral Transforms for Caustic Denoising: A Comparative Analysis for Monte Carlo Rendering.(ZOOM)

11:50-12:50

LNCS 3

Chair: Nadia Magnenat Thalmann, MIRALab, UNIGE

TVC 6 3D Modeling

Chair: Paul Zika, ORamaVR

LNCS 16

Chair: Thiago Freitas, MIRALab, UNIGE

  • Tao Peng, Yingying Wang, Li Li, Jiazhe Miao, Junping Liu and Xinrong Hu. GRD: Garment Reconstruction and Draping with Preserved Design Based on 2D Image.(ZOOM)

  • Yan Zhu, Yu Qian, Renlong Dai, Linbo Wang, Zhengyi Liu and Xianyong Fang. Towards More Accurate Human Reconstruction for Single RGB-D Images.

  • Lei Bi, Yige Peng, Dagan Feng and Jinman Kim. Semi-Mamba: Improving Medical Image Segmentation via Semi-Automatic Mamba Network.(ZOOM)

  • Yuanyuan Lin, Ju Dai, Junjun Pan, Feng Zhou and Junxuan Bai. Free-editing of Shape and Texture with Deformable Net for 3D Caricature Generation.(ZOOM)

  • Hao Xu, Yiqian Wu, Xiangjun Tang, Jing Zhang, Yang Zhang, Zhebin Zhang, Chen Li and Xiaogang Jin. FusionDeformer: Text-guided Mesh Deformation using Diffusion Models.

  • Jiayi Xu, Chenming Zhang, Weikang Zhu, Hongbin Zhang, Li Li and Xiaoyang Mao. Personalized Hairstyle and Hair Color Editing Based on Multi-Feature Fusion.(ZOOM)

  • Jiaqi Wu, Da Lu, Yu Tao, Hui Ding and Guoping Huo. ED-Net: Unified Enhancement-Denoising Deep Convolutional Network for Low-Light Mining Images.(ZOOM)

  • Ning Ni and Ligang Liu. Numerical Coarsening for Tetrahedral Meshes.(ZOOM)

  • Bing Yu, Shan Pan, Ruihao Sun, Wangyidai Lv and Youdong Ding. Realistic Image Super-Resolution with Generative Diffusion.(ZOOM)

12:50-13:50

LUNCH BREAK

First Parallel session

Room: Auditorium

Second Parallel Session

Room: H8-01-D

Third Parallel session

Room: H4-02-A

13:50-15:30

VRIH Session

Chair: Maher Ben Moussa, UNIGE

CAVW 3

Chair: Anderson Maciel, U. of Lisbon

LNCS 17

Chair: Marina Gavrilova, U.of Calgary

  • Philippe Latour and Marc Van Droogenbroeck. CURDIS: A Template for Incremental Curve Discretization Algorithms and its Application to Conics.

  • Yanbo Cheng, Yichen Jiang and Yingying Wang. Music-stylized Hierarchical Dance Synthesis with User Control.

  • Amir Azizi, Panagiotis Charalambous and Yiorgos Chrysanthou. DeepSafe:Advanced Deep Learning Approach for Disaster Victims Detection.(ZOOM)

  • Xiaoer Wu, Zhenhua Tan, Ziwei Cheng and Yuran Ru. STDNet: to Improve Lip Reading via Short-term Temporal Dependency Modeling.(ZOOM)

  • Yuka Komeda, Wataru Umezawa and Tomohiko Mukai. Acanthus Ornament Generation Using Layout Subdivisions with Parameterized Motifs.

  • Aleksander Sawicki. Behavioural gait biometrics in VR: Is the use of synthetic samples able to increase person identification metrics?(ZOOM)

  • Zhenhua Ou, Xueting Liu, Chengze Li, Zhenkun Wen, Ping Li, Zhijian Gao and Huisi Wu. Body Part Segmentation of Anime Characters.(ZOOM)

  • Lavanya Srinivasan and Lavanya Srinivasan. Automated Recognition of Gait Emotion.(ZOOM)

  • Li Meng, Morten Goodwin, Anis Yazidi and Paal Engelstad. A Manifold Representation of the Key in Vision Transformers.

  • Peng He, Liangjun Wang, Lei Xu, Wu Zhang and Wenhao Zhu. Fast mesh generation in multi-layer lattice Boltzmann simulation with moving boundaries.(ZOOM)

17:00-19:00

Visit Old Town and Cathedrale

19:00-21:30

Conference Dinner at Café Papon In Old Town

Thursday, July 4

CGI Conference Day 4

09:00-09:15

Welcome to CGI

09:15-10:00

CGI Keynote 3

Dr. Ping Li – The Hong Kong Polytechnic University

Exploration of Creative Media, Art and Design in Metaverse



Chair: Nadia Magnenat Thalmann, MIRALab, UNIGE

10:00-10:30

COFFEE BREAK

First Parallel session

Room: Auditorium

Second Parallel Session

Room: H8-01-D

Third Parallel session

Room: H4-02-A

10:30-11:50

TVC 7 Deep Learning for Graphics 2

Chair: Yang Wen, Shenzhen University, China

LNCS 4

Chair: Daniel Thalmann, EPFL

LNCS 18

Chair: Thiago Freitas, MIRALab, UNIGE

  • Tongshuai Yu, Ye Liu, Hao Liu, Ji Chen and Xing Wang. ParaLkResNet: An Efficient Parallel Convolutional Network for Image Classification.(ZOOM)

  • Yiguo Jiang, Xuhang Chen, Shuqiang Wang, Chi-Man Pun and Wei Feng. MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal.(ZOOM)

  • Xin Duan, Yu Cao, Renjie Zhang and Ping Li. Shadow-Aware Image Colorization.

  • Chao Song, Qingjie Chen, Frederick W. B. Li, Zhaoyi Jiang and Bailin Yang. Multi-Feature Fusion Enhanced Monocular Depth Estimation with Boundary Awareness.(ZOOM)

  • Xiao Liu, Xiaoping Che, Chenxin Qu, Haiming Liu, Jingxin Su and Xiaofei Di. Physiological Factors based Depression Assessment in Virtual Reality.(ZOOM)

  • Wantong Duan, Yongtang Bao and Yue Qi. SSCCPC-Net: Simultaneously Learning 2D and 3D Features with CLIP for Semantic Scene Completion on Point Cloud.(ZOOM)

  • Haipeng Wang. GPN: Generative Point-based NeRF.(ZOOM)

  • Junjie Liao, Mengxiao Yin, Ming Li, Congyang Zhu, Zhiqiang Yang and Feng Zhan. ALFC-Point: Adaptive Laplacian Feature Convolution Network for 3D Point Cloud Understanding.(ZOOM)

  • Yanru Wang, Song Wang, Hesong Wang, Hao Long and Hao Hu. Construction and Visual Validation of Low-carbon Development Evaluation System for Urban Agglomerations.(ZOOM)

  • Xinrong Hu, Jiwei Huang, Fei Fang, Tao Peng, Feng Yu, Kai Yang and Jia Chen. DesignGAN: Generation of hand-drawn garment sketches.(ZOOM)

  • Xinru Zhuo, Min Shi, Dengming Zhu, Guoqing Han and Zhaoxin Li. Unsupervised Real-time Garment Deformation Prdiction Driven by Human Body Pose and Shape.(ZOOM)

11:50-12:50

TVC 8 Rendering

Chair: Yang Wen, Shenzhen University, China

LNCS 5

Chair: Daniel Thalmann, EPFL

LNCS 19

Chair: Thiago Freitas, MIRALab, UNIGE

  • Geunwoo Oh and Bochang Moon. Joint Self-Attention for Denoising Monte Carlo Rendering.

  • Saskia Rabich, Patrick Stotko and Reinhard Klein. FPO++: Efficient Encoding and Rendering of Dynamic Neural Radiance Fields by Analyzing and Enhancing Fourier PlenOctrees.

  • Xuchen Wei, Rui Wang, Yuchi Huo and Hujun Bao. Refined Tri-directional Path Tracing with Generated Light Portal.

  • Yanjie Chen, Guoheng Huang, Xiaochen Yuan, Xuhang Chen, Yan Li, Chi-Man Pun and Junbing Quan. PDGC: Properly Disentangle by Gating and Contrasting for Cross-Domain Few-Shot Classification.(ZOOM)

  • Ashhadul Islam, Farida Mohsen, Zubair Shah and Samir Brahim Belhaouari. Introducing Radex: Adaptive Parameterized Feature Extraction from Medical Images.

  • Yifan Liu, Mingfu Yan, Hua He, Jiancheng Huang and Shifeng Chen. MambaDW: Semantic-Aware Mamba for Document Watermark Removal.(ZOOM)

  • Tong Wu, Song Wang and Xin Peng. Automated data exploration and analysis.(ZOOM)

  • Chengcheng Lv, Mincheng Wu, Xiufang Shi, Jiming Chen, Xiang Wu, Ce Shen and Hui Dong. Network Topology Recognition from Images via Window Detection.(ZOOM)

  • João Simões, Anderson Maciel, Catarina Moreira, Mauricio Sousa and Joaquim Jorge. SPARC: Shared Perspective with Avatar Distortion for Remote Collaboration in VR.

12:50-13:50

LUNCH BREAK

Room: Auditorium

Second Parallel Session

Room: H8-01-D

Third Parallel session

Room: H4-02-A

13:50-15:10

TVC 9 Simulation

Chair: Eckhard Hitzer, Christian University, Japan

LNCS 6

Chair: Hangyeol Kang, UNIGE

LNCS 20

Chair: Achilleas Filippidis, ORamaVR

  • Yuege Xiong, Xiaokun Wang, Yanrui Xu, Yalan Zhang, Jian Chang, Jian Jun Zhang and Xiaojuan Ban. Dual-Mechanism Surface Tension Model for SPH-Based Simulation.(ZOOM)

  • Siyan Zhu, Cheng Fang, Peng Yu, Xiao Zhai and Junjun Pan. Efficient Frictional Contacts for Soft Body Dynamics via ADMM.

  • Bastien Saillant, Florence Zara, Fabrice Jaillet and Guillaume Damiand. High-Order Elements in Position Based Dynamics.

  • Alon Flor and Mridul Aanjaneya. Spectral Reordering for Faster Elasticity Simulations. 

  • Jiahao Qin and Feng Liu. Mamba-Spike: Enhancing the Mamba Architecture with a Spiking Front-End for Efficient Temporal Data Processing.(ZOOM)

  • Jingyao Cai, Boyuan Cheng, Yingjie Xi and Xiaosong Yang. Survey on Multi-Person 3D Reconstruction from Monocular View. (ZOOM)

  • Sarra Aloui and Wang Yu. TunSLR-25: A New Static Tunisian Sign Language Recognition System.(ZOOM)

  • Yangyue Liu, Yong Hu and Xukun Shen. Expression Fusion to Enhance Video- and Speech-driven 3D Facial Animation.

  • Xinyi Zhang and Zheng Wang. The Establishment of a Hypoxia Cellular Morphology Model Based on Deep Convolutional Neural Networks and Intelligent Screening of Anti-Hypoxia Drugs.

  • Mihai-Adrian Loghin and Anca-Mirela Andreica. DeGraRec: 3D Deformable Object Reconstruction using Graph Neural Networks and Depth Estimation.(ZOOM)

15:10-15:40

COFFEE BREAK

15:40-17:00

Room: Auditorium

TVC 10 Geometry and Visualization

Chair: Eckhard Hitzer, Christian University, Japan

Room: H8-01-D

LNCS 7

Chair: Hangyeol Kang, UNIGE

Room: H4-02-A

LNCS 21

Chair: Achilleas Filippidis, ORamaVR

  • Qinsong Li, Yueyu Guo, Xinru Liu, Ling Hu, Feifan Luo and Shengjun Liu. Deformable Shape Matching with Multiple Complex spectral filter operators Preservation.(ZOOM)

  • Dhruv Meduri, Mohit Sharma and Vijay Natarajan. Jacobi Set Simplification for Tracking Topological Features in Time-Varying Scalar Fields.(ZOOM)

  • Moataz Abdelaal, Marcel Galuschka, Max Benjamin Zorn, Fabian Kannenberg, Achim Menges, Thomas Wortmann, Daniel Weiskopf and Kuno Kurzhals. Visual Analysis of Fitness Landscapes in Architectural Design Optimization.

  • Hanchao Li and Xinguo Liu. Strand-accurate Multi-view Facial Hair Reconstruction and Tracking.(ZOOM)

  • Jianxi He, Min Meng, Jigang Liu and Jigang Wu. Multi-scale Similarity Information Fusion for Unsupervised Cross-modal Retrieval.(ZOOM)

  • Yaping Jing, Ajmal Mian, Leo Zhang, Shang Gao and Xuequan Lu. 3D Face Recognition with Contrastive Learning Network on Low-quality Data.(ZOOM)

  • Somnath Dutta, Benjamin Russig and Stefan Gumhold. Enhanced Plant Phenotyping Through Spatio-Temporal Point Cloud Registration.(ZOOM)

  • Hao Tian, Yu Cao and P. Y. Mok. SewPCT: Sewing Pattern Reconstruction from Point Cloud with Transformer.(ZOOM)

  • Yongzheng Cui, Bolei Chen, Haonan Yang, Ping Zhong and Yu Sheng. Finding and Grasping: The Last-Mile of Object Goal Navigation.(ZOOM)

  • Juan Bayón Fernández, Joaquín Recas Piorno, Jonathan José Jiménez Jiménez and María Guijarro Mata-García. Blue Light Digital Filter with accurate color representation, contrast and quality.(ZOOM)

  • Achilleas Filippidis, Nick Marmaras, Michael Maravgakis, Alexandra Plexousaki, Manos Kamarianakis and George Papagiannakis. VR Isle Academy: A VR Digital Twin Approach for Robotic Surgical Skill Development.

  • Junaid Abdul Wahid, Muhammad Ayoub, Mingliang Xu, Xiaoheng Jiang, Shi Lei, Lifeng Li, Shabir Hussain, Ashfaque Khowaja and Yufei Gao. End-to-End Transformer Architecture with Novel Ensemble Learning Method Integrating CT Scans and Clinical Narratives for Brain Stroke Diagnosis.(ZOOM)

Friday, July 5

CGI Conference Day 5

09:00-09:15

Welcome to CGI

09:15-10:00

Panel: AI, LLMs, Vision:  Does Computer Graphics still exist as a domain today? 

Chaired by:  Prof Nadia Magnenat Thalmann, University of Geneva, Switzerland

Participants:

Prof. Marina Gavrilova, University of Calgary, Canada

Prof. Jinman Kim, University of Sydney, Australia

Prof. Ping, Li, PolyU, Hongkong

Prof. George Papagiannakis, ORamaVR and University of Crete

Prof. Daniel Thalmann, EPFL, Switzerland

Prof. Jian Jun Zhang, Bournemouth University, UK

10:00-10:30

COFFEE BREAK

First Parallel session

Room: Auditorium

Second Parallel session

Room: H8-01-D

Third Parallel session

Room: H4-02-A

10:30-12:10

TVC 11 Curves and Surfaces

Chair: Ursula Augsdorfer, Technical University, Graz, Austria

LNCS 8

Chair: Ping Li, PolyU, Hongkong

LNCS 22

Chair: Nadia Magnenat Thalmann, MIRALab, University of Geneva

  • Ryunosuke Yamada, Tokuo Tsuji, Tatsuhiro Hiramitsu, Hiroaki Seki, Toshihiro Nishimura, Yosuke Suzuki and Tetsuyou Watanabe. Fast and precise approximation of Minkowski sum of two rotational ellipsoids with a superellipsoid

  • Shuyang Zhu, Youlong Li, Jizhao Liu and Bin Li. An Automatic Framework for Quadrilateral Surface Reconstruction with Partitions from 3D Point Clouds.(ZOOM)

  • Saeedeh Barzegar Khalilsaraei, Alexander Komar, Jianmin Zheng and Ursula Augsdörfer. InceptCurves: Curve Reconstruction Using an Inception Network.

  • Andy Thai, Irmina Gradus-Pizlo, Zygmunt Pizlo, Hakan Sahin and M. Gopi. Automatic Segmentation and Implicit Surface Representation of Dynamic Cardiac Data.

  • Naoki Kita. PackMolds: Computational Design of Packaging Molds for Thermoforming.

  • Fanqian Meng, Ouli Luo, Hui Ding and Guoping Huo. SCAR-UNet: An Improved Res-UNet with Channel and Spatial Attention for Coal Maceral Image Segmentation.(ZOOM)

  • Tao Peng, Delang Peng, Li Li, Junping Liu, Zili Zhang and Xinrong Hu. DS-Seq: Deriving smooth 3D human motion sequences from video time cues.(ZOOM)

  • Zhenhui Li, Xin Cong and Lingling Zi. FMA-YOLO: An Algorithm for Detecting Vehicles and Pedestrians in Infrared Road Scenarios.(ZOOM)

  • Mingwei Cao, Siqi Nian and Jun Yi. DUE-MVSNet: Learning Multi-View Stereo Based on Dual Uncertainty Estimation.(ZOOM)

  • Muhammad Mujahid, Md Shamim Hossain, Asad Khan, Muhammad Awais Javeed, Arbelo Laulai and Zhangjin Huang. Reinforcement Learning Based improved Seam Carving using Special point and Alpha value for Optimal Content Preservation.

  • Diego Gomez, Julien Philip, Adrien Kaiser and Élie Michel. RRM: Relightable assets using Radiance guided Material extraction.

  • Heejun Lee, Peter A. J. Pijpker, Joep Kraeima, Lorenzo Amabili, Jos Roerdink, Fokie Cnossen, Peter van Ooijen and Jiri Kosinka. BoneStory: Visual Storytelling in 3D Virtual Surgical Planning for Bone Fracture Reduction.

  • Jiannan Ye, Zhenkai Zhong, Xiaoxu Meng and Xubo Yang. Neural Metameric Enhancement for Foveated Rendering.(ZOOM)

  • Le Ma, Hangyeol Kang, Nadia Magnenat Thalmann and Katarzyna Wac. TransSG: A Spatial-Temporal Transformer for Surgical Gesture Recognition.

  • Khairul Fadhli Mohammad, Alan Chalmers and Kurt Debattista. The Significance of Interaction in Determining Learning Outcomes in Serious Games.

12:10-12:50

LNCS 1

Chair: Reinold Preiner

Technical University, Graz, Austria

LNCS 9

Chair: Thiago Freitas

MIRALab-University of Geneva

  • Li Liu, Xinlei Zhou, Mingwei He, Feng Yu, Tao Peng, Xinrong Hu and Minghua Jiang. A Real-time Semantic Segmentation Network for Robotic Arm Grasp.(ZOOM)

  • Jia Chen, Xueping Xu, Fei Fang, Huanrong Jiang and Xinrong Hu. BISRM: Geotechnical borehole image super-resolution method based on conditional diffusion model.(ZOOM)

  • Guodong Zhang and Wenzhu Yang. LSBNet: Lightweight Symmetrically Balanced Network for Real-time Semantic Segmentation.(ZOOM)

  • Xingquan Cai, Yao Liu, Chenyu Li, Haiyan Ma and Haiyan Sun. Retinex-based Low-light Mural Image Enhancement with Color Correction.(ZOOM)

12:50-13:50

LUNCH BREAK

First Parallel session

Room: Auditorium

Second Parallel session

Room: H8-01-D

Third Parallel session

Room: H4-02-A

13:50-15:10

LNCS 2

Chair: Tristan Wirth, Technical University, Darmstadt, Germany

LNCS 10

Chair: Andy Thai, University of California, Irvine, USA

  • Yang Wen, Anyu Lai, Bo Qian, Hao Wang, Wuzhen Shi and Wenming Cao. Multiple weather images restoration using the task transformer and adaptive mixup strategy.(ZOOM)

  • Yixian Wang, Boheng Lin, Weiya Chen and Lin Wan. Efficient Low-polygon Building Model Generation with Opening Detection.(ZOOM)

  • Xingquan Cai, Shike Liu, Haoyu Song and Haiyan Sun. Decoupled Estimation of Human Pose and Shape for ICH Performance Video Based on L-C-HRNet.(ZOOM)

  • Yun Liu, Weiming Wang, Fu Lee Wang, Haoran Xie, Honghua Chen, Mingqiang Wei and Jing Qin. Shape Descriptor Guided Learning for Category-level Object Pose Estimation.(ZOOM)

  • Meng Sun, Jianlin Zhu, Bo Yang, Jin Huang and Xiao Zhang. Pedestrian Detection in Foggy Weather Through YOLOv8 based on FEAttention.(ZOOM)

  • Yang Yang, Jianlin Zhu, Bo Yang, Xiao Zhang and Jin Huang. An Improved YOLOv8-Based Rice Pest and Disease Detection.(ZOOM)

  • Hongjin Lyu, Hareeharan Elangovan, Paul Rosin and Yu-Kun Lai. SCD: Statistical Color Distribution-based Objective Image Colorization Quality Assessment.(ZOOM)

  • Wang Hesong, Wang Song, Wang Yanru and Long Hao. DM-Vis: a graph-based data reconnaissance system for multi-domain urban data.(ZOOM)

15:10-15:40

CGI Awards and Closing session

Download the papers

The pdf versions of the articles are available from the following links: