Computer Vision for Metaverse Workshop 2023

ICCV 2023

Paris, France

Date & Time: 

Tuesday, October 3rd, 2023

Virtual attendance link: https://fb.zoom.us/j/97232775474?pwd=ak80V2F5TE16TFhKUU5KYXg0ampkZz09

Workshop overview: 

Computer Vision (CV) research plays an essential role in enabling the future applications of Augmented Reality (AR), Virtual Reality (VR), and Mixed Reality (MR), which are nowadays referred to as the Metaverse. Building the Metaverse requires CV technologies to better understand people, objects, scenes, the world around us, and better render contents in more immersive and realistic ways. This brings new problems to CV research and inspires us to look at existing CV problems from new perspectives. As the general public grows interest and industry put more efforts in Metaverse, we think it is a good opportunity to organize a workshop for the computer vision community to get together to showcase our latest research, discuss new directions and problems, and influence the future trajectory of Metaverse research and applications. 

Workshop topics:

In this workshop, we emphasize on the social aspect of Metaverse and focus on CV problems that help people connect and interact with each other. To this end, we propose to mainly focus on four topics as follows.

• Generative AI:

  • Multi-media generation: image generation, video generation

  • 3D generation: avatar generation, scene generation, 3D object/assets generation

• People Understanding & Generation

  • Methods, algorithms, systems for human understanding, augmentation, presentation, and multi-modal interaction.

  • Efficient solutions for person detection, segmentation, pose/shape estimation, and 2D and 3D body/hand/face/eyes tracking, capture and reconstruction.

  • Face body generation and temporally realistic 2D/3D human representations from visual sensors across a range of devices.

• Scene & Object Understanding and Generation

  • Methods, algorithms and systems for scene and object understanding

  • Efficient solutions for scene modeling using planar geometry, surface norm, mesh and depth estimation, scene detection and 3D reconstruction, and 2D and 3D object tracking.

  • Generative models for scene and object generation in 2D, video, and 3D.

• Graphics and Rendering

  • Computational photography, including digital image processing, enhancement and in-camera computation.

  • Computer graphics for 3D scene and body modeling, generation and rendering for synthetic data generation.

  • Efficient and generic novel-view synthesis for on-device applications.

Program summary:

This workshop will have paper submissions and invite leading researchers to give talks on their work. The full day event (8 hours in total) will consist of 9 invited talks for 4.5 hours (30 minutes each), talks on accepted papers for 3 hours, two panel discussions for 1 hour, and a lunch break for 30 minutes. This workshop targets CV researchers have worked on or are interested in working on Metaverse related topics. 

Detailed program to be announced.