The AI for Content Creation (AI4CC) workshop at CVPR brings together researchers in computer vision, machine learning, and AI. Content creation is required for simulation and training data generation, media like photography and videography, virtual reality and gaming, art and design, and documents and advertising (to name just a few application domains). Recent progress in machine learning, deep learning, and AI techniques has allowed us to turn hours of manual, painstaking content creation work into minutes or seconds of automated or interactive work. For instance, generative adversarial networks (GANs) can produce photorealistic images of 2D and 3D items such as humans, landscapes, interior scenes, virtual environments, or even industrial designs. Neural networks can super-resolve and super-slomo videos, interpolate between photos with intermediate novel views and even extrapolate, and transfer styles to convincingly render and reinterpret content. In addition to creating awe-inspiring artistic images, these offer unique opportunities for generating additional and more diverse training data. Learned priors can also be combined with explicit appearance and geometric constraints, perceptual understanding, or even functional and semantic constraints of objects.
AI for content creation lies at the intersection of the graphics, the computer vision, and the design community. However, researchers and professionals in these fields may not be aware of its full potential and inner workings. As such, the workshop is comprised of two parts: techniques for content creation and applications for content creation. The workshop has three goals:
More broadly, we hope that the workshop will serve as a forum to discuss the latest topics in content creation and the challenges that vision and learning researchers can help solve.
Welcome! -
Deqing Sun (Google)
Lingjie Liu (University of Pennsylvania)
Yuanzhen Li (Google)
Sergey Tulyakov (Snap)
Huiwen Chang (OpenAI)
Lu Jiang (ByteDance)
Yijun Li (Adobe)
Jun-Yan Zhu (Carnegie Mellon University)
James Tompkin (Brown University)
We call for papers (8 pages not including references) and extended abstracts (4 pages not including references) to be presented at the AI for Content Creation Workshop at CVPR. Papers and extended abstracts will be peer reviewed in a double blind fashion. Authors of accepted papers will be asked to post their submissions on arXiv. These papers will not be included in the proceedings of CVPR, but authors should be aware that computer vision conferences consider peer-reviewed works with >4-pages to be in violation of double submission policies, e.g., both CVPR and ECCV. We welcome both novel works and works in progress that have not been published elsewhere.
In the interests of fostering a free exchange of ideas, we will also accept for poster presentation a selection of papers that have been recently published elsewhere, including at CVPR 2024; these will not be peer reviewed again, and are not bound to the same anonymity and page limits. A jury of organizers will select these papers.
Paper submissions for 4- and 8-page novel work are double blind and in the CVPR template. You are welcome to include appendices in the main PDF, and upload supplemental material such as videos. There are no dual submissions—please do not submit work for peer review to two workshops simultaneously.
Paper submission deadline: March 21st 2024 23:59 US Pacific Time (PDT)
Acceptance notification: ~April 26th 2024
Submission Website: OpenReview
The best student papers will be acknowledged with a prize.
Reviewing: We accept self-nominations for reviewers: Apply here (Google Form).
This is an excellent opportunity for junior researchers to gain experience in reviewing. Experienced reviewers can also apply to be a meta-reviewer (similar to Area Chair), again to gain experience. Meta-reviewers will handle at most 5 papers. Thank you!
Travel awards (2024): We have travel awards to sponsor under-represented students to attend the workshop. Students will also have an opportunity to interact with invited workshop speakers at a social occasion. Apply here (Google Form).
We seek contributions across content creation, including but not limited to techniques for content creation:
We also seek contributions in domains and applications for content creation:
Click ▶ to jump to each talk!
Morning session:Time PDT | |||
---|---|---|---|
09:00 | Welcome and introductions | 👋 | |
09:10 | Ben Mildenhall (Google) — neural fields | ||
09:40 | Ryan Murdock — ML+Art | ||
10:10 | Coffee break | ☕ | |
10:20 | Angela Dai (TU Munich) — 3D | ||
10:50 | Tim Salimans (Google) — images, video | ||
11:20 | Poster session 1 - West Exhibit Hall #93-#107
|
||
12:30 | Lunch break | 🥪 |
Time PDT | |||
---|---|---|---|
13:30 | Oral session + best paper announcement
|
||
14:00 | Jiajun Wu (Stanford University) — representations | ||
14:30 | Shizhao Sun (Microsoft) — design | ||
15:00 | Coffee break | ☕ | |
15:15 | Yuanzhen Li (Google) — images, video | ||
15:45 | Xingang Pan (NTU) — DragGAN — late breaking speaker! | 🦜 | |
16:15 | Panel discussion — AI Hopes and Fears for Practical Content Creation
|
🗣️ | |
17:15 | Poster session 2 - West Exhibit Hall #94-#107
|