We present an approach for highly accurate bottom-up object segmentation. Given an image, the approach rapidly generates a set of regions that delineate candidate objects in the image. The key idea is to train an ensemble of figure-ground segmentation models...
Authors
Philipp Krähenbühl
Related Content
Finexus: Tracking Precise Motions of Multiple Fingertips Using.
With the resurgence of head-mounted displays for virtual reality, users need new input devices that can accurately track their hands.
Dense Monocular Depth Estimation in Complex Dynamic Scenes
We present an approach to dense depth estimation from a single monocular camera that is moving through a dynamic scene.
Feature Space Optimization for Semantic Video Segmentation
We present an approach to long-range spatio-temporal regularization in semantic video segmentation. Temporal regularization in video is challenging because both.
Direct Sparse Odometry
We propose a novel direct sparse visual odometry formulation. It combines a fully direct probabilistic model (minimizing a photometric error).