Wenxuan Wu is a Senior Software Engineer in Corvallis with eight years of hands-on expertise at the intersection of computer vision and deep learning, specializing in 3D DNNs, Visual SLAM, stereo vision and 3D reconstruction. He led development of end-to-end autonomous driving simulation and novel view synthesis systems at Momenta, built a BEVFormer-based auto-labeling pipeline, and developed a road-surface reconstruction algorithm comparable to industry leaders. His PhD work produced PointConv, an efficient convolution for 3D point clouds that cut memory use dramatically while improving ScanNet segmentation accuracy, reflecting a rare combination of theoretical insight and production-grade implementation. Prior research internships at Waymo, Facebook Reality Labs, Nuro and Intel Labs further sharpened his perception and SLAM skills in real-world robotics and AR/VR settings. Comfortable moving projects from research to deployed systems, he also brings project initiation and management experience across complex perception stacks.
8 years of coding experience
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Oregon State University
Master's degree Laser and Optical Engineering, Master's degree Laser and Optical Engineering at Beijing Institute of Technology
PointPWC-Net is a deep coarse-to-fine network designed for 3D scene flow estimation from 3D point clouds.
Contributions:23 commits, 3 PRs, 15 pushes in 7 months
3d-scenepoint-cloudsfineestimationpoint
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.