CVEU Workshop

About CVEU

This workshop is for the 4th installment of the AI for Creative Video Editing and Understanding (CVEU) focusing on the future of generative visual art, which follows its success on the previous launch at ICCV'23, ECCV'22 and ICCV'21.

The workshop brings together researchers, artists and entrepreneurs working on computer vision, machine learning, computer graphics, human computer interaction, and cognitive research.

It aims to bring awareness of recent advances in machine learning technologies to enable assisted creative visual content creation and understanding.

Program

Discuss recent advances in creative visual content editing, generation and understanding, including:

How to design intuitive video editing and creation tools?

How do humans and AI collaborate together to inspire creativity?

How can AI help to reduce the human cost of video productions?

How to deal with the biases and threats by using AI?

A special film session showcasing submissions to AI ShortFest 2023, exciting new creative Film Festival. Get a sneak peek of this year's trailer:

Keynote Speakers

Tim Brooks
Research Scientist@OpenAI
Co-lead of Sora Project

Jeffrey P. Bigham
Professor@CMU
Lead of Human-Centered Machine Intelligence@Apple

Aaron Hertzmann
Principal Scientist
Adobe Research

Anastasis Germenidis
Co-founder, CTO
RunwayML

Yuge (Jimmy) Shi
Research Scientist
DeepMind
Author of Genie

Jianchao Yang
Head of Intelligent Creation Technology
ByteDance

Dumitru Erhan
Research Director
Google

Jun-Yan Zhu
Professor
Carnegie Mellon University

Jack Parker-Holder
Research Scientist
DeepMind
Author of Genie

Jia-Bin Huang
Professor@UMD
Research Scientist@Meta

Chenlin Meng
Co-Founder, CTO
Pika

Paul Debevec
Chief Research Officer, Eyeline Studios

Taesung Park
Chief Scientist
Reve AI

Detailed Program

Schedule	Seattle Time 2024-06-18 8:00 AM
Warm-up Session	08:00 AM - 08:25 AM	-
Workshop Opening Remarks	08:25 AM - 08:30 AM	-
Session I - Is AI Art? How Machines Change Art? Keynote I by Aaron Hertzmann Keynote II by Jiabin Huang Keynote III by Anastasis Germanidis Roundtable Discussion (30 mins)	08:30 AM - 10:00 AM	-
Session II - AI Creative Tools, Visual Effects and Movie Industry Keynote I by Taesung Park Keynote II by Tim Brooks Keynote III by Paul Debevec Roundtable Discussion, plus Jiaming Song, Jon Barron (30 mins)	10:20 AM - 11:50 AM	-
Launch Break	11:50 AM - 2:00 PM	-
Session III - Big Industry Models Keynote I by Jianchao Yang Keynote II by Dumitru Erhan Keynote III by Chenlin Meng Roundtable Discussion, plus Maneesh Agrawala (30 mins)	02:00 PM - 03:30 PM	-
Coffer break	03:30 PM - 04:00 PM	-
Session IV - Problems of Generative Models in Practice Keynote I by Junyan Zhu Keynote II by Jack Parker-Holder and Jimmy Shi Keynote III by Jeffrey Bigham Roundtable Discussion (30 mins)	04:00 PM - 05:30 PM	-
Closing Remarks	05:30 PM - 05:40 PM	-

Participants from

Papers Presentation

Title	Venue	Link
As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors	CVPR'24	Paper Webpage
Posterior Distillation Sampling	CVPR'24	Paper Webpage
RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models	CVPR'24 (highlight)	Paper Webpage
Look, Listen and Recognise: character-aware audio-visual subtitling	ICASSP'24	Paper Webpage
Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models	CVPR'24	Paper Webpage
High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization	CVPR'23	Paper Webpage

Call for Submission

Topics

This workshop brings together researchers working on computer vision, machine listening, computer graphics, human-computer interaction, and cognitive research. It aims to bring awareness of recent advances in machine learning technologies to enable assisted creative-video creation and understanding. The workshop will include invited talks by experts in the area and give the community opportunities to share their work via oral and poster presentations. We encourage practitioners, designers, students, post-docs, and researchers to submit work describing new ideas, work-in-progress, and previously or concurrently published research. Topics of interest include but are not limited to:

Computational Video Editing
Computational Videography/Virtual Cinematography
Video Shortening and Manipulation
Video Description and Storyboarding
Video Search and Retrieval
Human-centric Video Understanding
Event/Story Understanding
Emotion/Sound Recognition
Generative Adversarial Network for Video
Foundataion Models for Video
Neural Rendering for Video
VR/AR/Panorama Video
Dataset and Evaluation

Invited Submission

This CVPR24 edition, we only run an invited paper track. Other tracks will come back in our next edition. The Invited Submission Track welcomes published papers on the topics summarized above. We will invite the accepted papers to be presented during the workshop.

Submission Guidelines

The papers submitted to the Invited Submission Track must be published work (e.g., accepted by CVPR24) related to topics of the CVEU workshop. All the submitted papers will have the opportunity to be presented during the workshop.

Please complete this Google Form to submit your paper.

Important Dates

Paper submission deadline: May. 4th, 23:59 Pacific Time

Acceptance notification to authors: May. 10th, 23:59 Pacific Time

Presentation material deadline: TBD

Organizers

The Future of Generative Visual Art

About CVEU