4 papers
Back to the Feature: Zero-Shot 6DoF Pose Estimation via Dense Local Features
Ali Rafiaei, Michael Greenspan
We present B2TFPose, a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images. Using a single frozen DINOv3 vision transformer as its only pretra…
CollideNet: Hierarchical Multi-scale Video Representation Learning with Disentanglement for Time-To-Collision Forecasting
Nishq Poorav Desai, Ali Etemad, Michael Greenspan
Time-to-Collision (TTC) forecasting is a critical task in collision prevention, requiring precise temporal prediction and comprehending both local and global patterns encapsulated…
Berry-Esseen bounds for step-reinforced random walks
Zhishui Hu
We study both the positively and negatively step-reinforced random walks with parameter . For a step distribution with finite second moment, the positively step-reinforced r…
Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation
Yangzheng Wu, Michael Greenspan
We address the simulation-to-real domain gap in six degree-of-freedom pose estimation (6DoF PE), and propose a novel self-supervised keypoint voting-based 6DoF PE framework, effect…