Doctoral Defense - Abhinav Kumar

About the Event

Department: Computer Science and Engineering

Michigan State University

Ph.D. Dissertation Defense

November 25, 2024 at 2:00 PM EST

3105 Engineering Building

Abstract:

Abstract Title: Generalizing Monocular 3D Object Detection
Name: Abhinav Kumar
Advisor Name: Xiaoming Liu

Monocular 3D object detection (Mono3D) is a fundamental computer vision task that estimates an object’s class, 3D position, dimensions, and orientation from a single image. Its applications, including autonomous driving, augmented reality, and robotics, critically rely on accurate 3D environmental understanding. This thesis addresses the challenge of generalizing Mono3D models to diverse scenarios, including occlusions, datasets, object sizes, and camera parameters. To enhance occlusion robustness, we propose a mathematically differentiable NMS (GrooMeD-NMS). To improve generalization to new datasets, we explore depth equivariant (DEVIANT) backbones. We address the issue of large object detection, demonstrating that it’s not solely a data imbalance or receptive field problem but also a noise sensitivity issue. To mitigate this, we introduce segmentation in bird’s-eye view with dice loss (SeaBird). Finally, we analyze the extrapolation of Mono3D models to unseen camera heights and improve Mono3D generalization in such out of distribution settings.