Overview
Welcome to the 2nd Workshop on AI for Content Generation, Quality Enhancement and Streaming at ICCV 2025 (Hawaii) 🌴🌅🌊
After the success of the 1st edition at CVPR 2024... we repeat and improve location!
This workshop focuses on unifying new streaming technologies, computer graphics, and computer vision, from the modern deep learning point of view. Streaming is a huge industry where hundreds of millions of users demand everyday high-quality content on different platforms.
Computer vision and deep learning have emerged as revolutionary forces for rendering content, image and video compression, enhancement, and quality assessment.
From neural codecs for efficient compression to deep learning-based video enhancement and quality assessment, these advanced techniques are setting new standards for streaming quality and efficiency.
Moreover, novel neural representations also pose new challenges and opportunities in rendering streamable content, and allowing to redefine computer graphics pipelines and visual content.
2024 Photo Gallery & Slides (CVPR)
Call for Papers
We welcome papers addressing topics related to VR, streaming, efficient image/video processing and compression. The topics include:- Efficient Computer Vision
- Model optimization and Quantization
- Image/video quality assessment
- Image/video super-resolution and enhancement
- Compressed Input Enhancement
- on-device & edge processing
- Generative Models (Image & Video)
- DeepFakes
- Vision Language Models
- Real-time Rendering
- Neural Compression
- Computer Graphics
Submission site: https://cmt3.research.microsoft.com/AIGENS2025
Submission Guidelines (Click to see)
- A paper submission has to be in English, in pdf format, and at most 8 pages (excluding references) following ICCV style. The paper format must follow the same guidelines as for all ICCV 2025 submissions https://iccv.thecvf.com/Conferences/2025/AuthorGuidelines
- Dual submission is not allowed. If a paper is submitted also to ICCV and accepted, the paper cannot be published both at the ICCV and the workshop. If the paper is under review elsewhere, it cannot be submitted here.
- The review process is double blind. Authors do not know the names of the chair/reviewers of their papers. Reviewers do not know the names of the authors.
- Accepted papers will be included in ICCV 2025 conference proceedings.
Important Dates (TBU)
| Paper submission deadline (& ICCV resubmissions) | 8th July, 2025 (AoE) |
| Paper decision notification (firm) | 11th July, 2025 |
| Camera ready deadline (firm) | 18th August, 2025 |
CMT Acknowledgement (click)
The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.Keynote Speakers
Dr. Yuki Mitsufuji is a Lead Research Scientist and the VP of AI Research at Sony AI, as well as a Distinguished Engineer at Sony Group Corporation. He earned his PhD in Information Science & Technology from the University of Tokyo. At Sony, he leads the Creative AI Lab and the Music Foundation Model Team, focusing on advancing AI applications in music and sound, contributing to projects like music restoration and soundtrack enhancement. In addition to his role at Sony, he was a specially appointed associate professor at Tokyo Institute of Technology from 2022 to 2025, where he lectured on generative models.
Edward Liu Shiqiu (Edward) Liu is a Director and Distinguished Research Scientist at NVIDIA. His teams spearhead the research of integrating cutting-edge AI with traditional computer graphics, advancing the Pareto curve of rendering quality and performance. This research has been instrumental in the development of renowned products like DLSS. Prior to this, Shiqiu was a core contributor to the advancements of real-time ray tracing in games at NVIDIA.
Invited Speakers
Víctor Perez
krea.ai
Xiaoyu Wang
Topaz Labs
JIN Yeying
Tencent
Agrim Gupta
DeepMind
Zhiqiang Lao
Futurewei Technologies
Schedule: 317 B, 9am - 5pm, Mon 20th October
| Time | Session | Speaker |
|---|---|---|
| 09:00 - 09:15 | Welcome & Opening | Marcos V. Conde |
| 09:15 - 09:25 | VidMP3: Video Editing by Representing Motion with Pose and Position Priors | Sandeep Mishra (University of Texas at Austin) |
| 09:25 - 09:35 | LSSGen: Leveraging Latent Space Scaling in Flow and Diffusion for Efficient Text to Image Generation | SJyun-Ze Tang (Inventec Corporation) |
| 09:35 - 10:45 | C2D-ISR: Optimizing Attention-based Image Super-resolution from Continuous to Discrete Scales | Yuxuan Jiang (University of Bristol) |
| 09:45 - 10:00 | Multi-Scale Contrastive-Adversarial Distillation for Super-Resolution | Donggeun Ko (AiM Future) |
| 10:00 - 10:15 | Coffee Break | |
| 10:15 - 11:00 | Keynote: Advances in Audiovisual Generative Models | Yuki Mitsufuji (Sony AI) |
| 11:00 - 11:30 | From Creation to Perception: Generative AI for Content Generation | Jin Yeying (Tencent) |
| 11:30 - 12:15 | 3D Rendering and Simulations | Jimmy Lao (Futurewei) |
| 12:15 - 12:30 | SILO: Solving Inverse Problems with Latent Operators | Sean Man (Technion) |
| 12:30 - 13:30 | Lunch Break | |
| 13:30 - 14:15 | Keynote: DLSS 4 and Beyond -- Research, Products, and Prospects | Edward Liu (NVIDIA) |
| 14:15 - 14:45 | Professional Image and Video Quality with Generative AI | Xiaoyu Wang (Topaz Labs) |
| 14:45 - 15:15 | Shipping Generative Tools at Scale | Víctor Pérez (Krea.ai) |
| 15:15 - 16:00 | World Models: Veo2, Genie3, and beyond | Agrim Gupta (DeepMind) |
Organizers
Marcos V. Conde ✉️
University of Würzburg
Radu Timofte
University of Würzburg
Julian Tanke
Sony AI
Eduard Zamfir
University of Würzburg
Takashi Shibuya
Sony AI
Program Committee and Advisors
Radu Timofte (University of Würzburg)
Eduard Zamfir (University of Würzburg)
Jingzhi Li (University of Würzburg)
Jonas Brenig (University of Würzburg)
Tim Seizinger (University of Würzburg)
Ioannis Katsavounidis (Meta)
Ryan Lei (Meta)
Cosmin Stejerean (Meta)
Heather Yu (Futurewei Technologies)
Zhiqiang Lao (Futurewei Technologies)
Zhi Li (Netflix)
Ren Yang (Microsoft)
Varun Jain (Microsoft)
Saman Zadtootaghaj (Sony Interactive Entertainment)
Nabajeet Barman (Sony Interactive Entertainment)
Abhijay Ghildyal (Sony Interactive Entertainment)
Julian Tanke (Sony AI)
Takashi Shibuya (Sony AI)
Yuki Mitsufuji (Sony AI)
Fan Zhang (University of Bristol)
Past Invited Speakers
Alan Bovik
University of Texas
Lucas Theis
Google DeepMind
Kelvin C.K. Chan
Google DeepMind
Ryan Lei
Meta
Christos Bampis
Netflix
Past/Present Sponsors, Organizers and Collaborators
