Xindi Wu
MOST: Lidar Panoptic Segmentation and Tracking without Bells and Whistles
Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images
Description: Personal webiste of Francesco Ferroni
I am a principal researcher at NVIDIA . My current interests are multi-modal models (i.e. text+vision), zero/few-shot and open-set learning, and NeRFs.
Prior to NVIDIA, I was a software engineering manager at ArgoAI , where I led multiple teams working on computer vision and machine learning for autonomous vehicles, primarily in the context of onboard perception and mapping/localization.
I enjoy being at the interface of large-scale engineering projects and cutting edge academic research. I have a track record of delivering innovative solutions to machine learning problems, either embedded in robots or in the cloud.
Xindi Wu
MOST: Lidar Panoptic Segmentation and Tracking without Bells and Whistles
Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images