Qiqi Hou

I am a machine learning researcher at Qualcomm AI Research. Much of my current research is about computer vision and computer graphics, such as LVM, 3DGS, stable diffusion, data compression, etc. Before that, I received my Ph.D. and M.E. degrees from Portland State University and Xi'an Jiaotong University in 2023 and 2017, respectively, where I was advised by Feng Liu and Jinjun Wang, respectively.

Email  /  CV  /  Google Scholar  /  Github

We introduce Weighted Sum Rendering, which uses weighted sums to approximate alpha blending, eliminating the need for sorting and avoiding popping artifacts.

We propose an asymmetric auto-encoder to compress the graphics texture.

We propose a parallel codec for fast and efficient low-latency stereo video compression.

We accelerate Monte-Carlo rendering via super-resoultion guided by high-resolution fast-to-compute auxiliary features.

We propose a perceptual quality metric dedicated to video frame interpolation.

We accelerate the Monte-Carlo rendering via multiple resolution sampling. We also introduce a large scale ray-tracing dataset - BCR dataset.

We can estimate the alpha matte and foreground simultaneously.

A face align recurent network to help avoid over-strong early stage regressors and over-weak later stage regressors.

Last updated: Oct, 2022. Template from here.