A Gaussian process is a concept that always comes next to Bayesian linear regression. Both approaches have strong advantages over measuring the uncertainty in predictions. A common saying on this is that knowing the uncertainty of a deep neural network’s (DNN) output is critical for handling wildly unrelated incoming data and safely reacting to it. In my case, I always preferred clear numbers instead of probabilities and distributions. Nowadays, however, I began to realize the importance of knowing how confident I can say about my DNN’s output and had to give it a try. …
S. Saito, Z. Huang, R. Natsume, S. Morishima, A. Kanazawa, and H. Li, “PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization,” ICCV, 2019, pp. 2304–2314.
University of Southern California
USC Institute for Creative Technologies
University of California, Berkeley
This paper proposed a novel implicit function that can create a mesh surface with RGB texture value in 3D space from a single-view image or multi-view images. I believe the key contributions of this work are in two concepts. First, the design of an implicit function that decodes pixel-aligned feature vectors to capture ambiguous clothed human body…
Oftentimes, fundamental mathematics I learned in the past became unclear when applied in deep learning and PCA is one of them. In this article, I want to emphasize the practical aspect of PCA in research and cover some of the mathematical backgrounds. Also, I’ve implemented the whole process in Google Colab for anyone who wants to follow through in practice.
Principal component analysis (PCA) is the process of computing the principal components and using them to perform a change of basis on the data, sometimes using only the first few principal components and ignoring the rest.
Following Wikipedia’s definition above…
Y. Chen, T. Yang, X. Zhang, G. Meng, X. Xiao, and J. Sun, “DetNAS: Backbone Search for Object Detection,” NeurIPS, 2019, pp. 1–11.
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
This paper proposed a novel method to search backbones in object detection which was previously a challenging task due to optimization and inefficiency problems. I believe the key contributions of this work are in two concepts. First, the design of supernet to enable pre-training which was hard to do in Neural Architecture Search (NAS) for the object detection tasks. …
I’ve recently had a chance to set up our lab’s remote server and was hard to find a clear guideline for what I wanted. I was trying to manage each user’s server usage well-contained inside a Docker while being able to efficiently upload the local python project. Please note that this article is based on a local connecting to a Docker inside a Ubuntu remote server.
I had a doubt about using Docker and because this is my first time using it, I kept wondering if this really is the best choice. Even though Docker provides a neat way to…
C.-Y. Weng, B. Curless, and I. Kemelmacher-Shlizerman, “Photo Wake-Up: 3D Character Animation from a Single Photo,” CVPR, 2019, pp. 5908–5917.
UW Reality Lab
Paul G. Allen School of Computer Science and Engineering
University of Washington
This paper proposed a method that can create an animation of a person from an image. I believe the key contributions of this work is in the proposed method of mesh reconstruction by silhouette matching to improve the reality of the reconstructed model compare to the previous work which only works on very general looking human. …
The concept of Bayesian is something that just crashed into my life when I got into college that always confused me and never really got to grasp the whole of it. I happen to be able to only fully digest the Frequentist view of the world and as I was studying the Bayesian theorem and Bayesian Linear Regression, I found it very difficult to comprehend fully. This post will go through struggles I’ve had in understanding the Bayesian point of view and clear up some vague ideas about it. …
Q. Wu, J. Zhang, Y.-K. Lai, J. Zheng, and J. Cai, “Alive Caricature from 2D to 3D,” CVPR, 2018, pp. 7336–7345.
University of Science and Technology of China, China
Cardiff University, UK
Nanyang Technological University, Singapore
This paper proposes a 3D reconstruction method from an input 2D caricature image which has difficulties capturing such exaggerated styles that are quite out of boundaries among regular 3D mesh dataset. I believe the key contribution of this work lies in the new local deformation gradient that extends to the deformation space. …
Like everyone else, coming up with a new year’s resolution is the first thing I do on the first day of every year. I happen to realize that writing down my daily thoughts or what you’ve learned can be quite effective in realizing what’s most important in my life and what to do on the next day. Also when you feel like you are stuck on the same track every day, it tells you what’s different from the other day. …