Howard Zhang

I am a 3rd year PhD student at UCLA where I am advised by Prof. Achuta Kadambi. My research interests include computer vision and computational imaging, particularly in the blending of physics and AI.

I attended UC Berkeley for my undergrad where I was fortunate to work with Professor Kristofer Pister on robotics and AI.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github  /  LinkedIn

Representative/Recent papers are highlighted

We propose a loss function for latent diffusion models that improves the perspective accuracy of generated images, allowing us to create synthetic data that helps improve SOTA monocular depth estimation models.

We introduce a pipeline that uses the power of light-transport physics to collect a large dataset of paired clear and weathered frames to train a SOTA model on weather removal.

We present a method for inferring dense depth from a camera image and a sparse noisy radar point cloud.

We propose a large-scale dataset of real-world rainy and clean image pairs and a method to remove degradations, induced by rain streaks and rain accumulation, from the image.