Computer Vision News - July 2022

BEST OF CVPR 30 Exclusive Interview space of the debris that we’re trying to capture, so we need to be able to trainour deepnetworks orwhatever machine learning model we have on synthetic images, but they need to work in space. The other aspect is that we don’t have access to large clusters of GPUs in space. We have FPGAs and small CPUs. We need networks and machine learning models that work in real-time on minimal computer vision. There’s the whole aspect of network compression, pruning, and quantization to make things work in real-time. When did you graduate with your PhD? I graduated in early 2009. What has happened since then? Many things! First, I went to do a postdoc at UC Berkeley with Trevor Darrell. I was there for a year and a half, working on 3D shape and non- rigid reconstruction. Then I moved to TTI in Chicago. I continued working on a similar topic. A bit of 3D human pose estimation as well. ThenImovedtoAustralia. Ihadasenior researcher position there. That’s where I started broadening my scope, working on Riemannian geometry for computer vision, visual recognition, segmentation, andmany different problems. Is that where you took the famous photograph of yourself with the cowboy hat? Exactly! [laughs] It’s made of kangaroo leather! I was in Australia for three and a half years. My first daughter was born in Australia. My Can you tell us more about the research side of your work? As I said, there’s a computer vision part at ClearSpace, but what we’re doing at ClearSpace is quite applied. We need things to work three years from now, and even that’s late. A whole world of research must be done to go beyond what we’re focusing on now at ClearSpace, which is one specific debris. We know the shape of the debris, so we have everything at hand to capture it, but we need to generalize to completely arbitrary debris that can result from a collision and have any shape. There’s much work on how to generalize not only to new debris but to imaging conditions. We don’t have images from