no code implementations • 31 Dec 2023 • Wan-Duo Kurt Ma, J. P. Lewis, W. Bastiaan Kleijn
Within recent approaches to text-to-video (T2V) generation, achieving controllability in the synthesized video is often a challenge.
no code implementations • 26 Sep 2023 • Wan-Duo Kurt Ma, Muhammad Ghifary, J. P. Lewis, Byungkuk Choi, Haekwang Eom
This paper describes FDLS (Facial Deep Learning Solver), which is Weta Digital's solution to these challenges.
1 code implementation • 10 Jul 2023 • Guoqiang Zhang, J. P. Lewis, W. Bastiaan Kleijn
In our work, it is found that applying BDIA to the EDM sampling procedure produces consistently better performance over four pre-trained models.
no code implementations • 29 Jun 2023 • Sharif Elcott, J. P. Lewis, Nori Kanazawa, Christoph Bregler
Alpha matting is widely used in video conferencing as well as in movies, television, and social media sites.
no code implementations • 25 Feb 2023 • Wan-Duo Kurt Ma, J. P. Lewis, Avisek Lahiri, Thomas Leung, W. Bastiaan Kleijn
Text-guided diffusion models such as DALLE-2, Imagen, eDiff-I, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt describing the desired image content.
3 code implementations • 5 Aug 2019 • Wan-Duo Kurt Ma, J. P. Lewis, W. Bastiaan Kleijn
We introduce the HSIC (Hilbert-Schmidt independence criterion) bottleneck for training deep neural networks.
1 code implementation • International Journal of Computer Vision 2010 • Simon Baker, Daniel Scharstein, J. P. Lewis, Stefan Roth, Michael J. Black, Richard Szeliski
The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance.