EG 2021 - Posters

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633004

Browse

Browsing EG 2021 - Posters by Subject "Interest point and salient region detections"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Fast and Robust Registration and Calibration of Depth-Only Sensors
    (The Eurographics Association, 2021) Mühlenbrock, Andre; Fischer, Roland; Weller, René; Zachmann, Gabriel; Bittner, Jirí and Waldner, Manuela
    The precise registration between multiple depth cameras is a crucial prerequisite for many applications. Previous techniques frequently rely on RGB or IR images and checkerboard targets for feature detection, partly due to the depth data being inherently noisy. This limitation prohibits the usage for use-cases where neither is available. We present a novel registration approach that solely uses depth data for feature detection, making it more universally applicable while still achieving robust and precise results. We propose a combination of a custom 3D registration target - a lattice with regularly-spaced holes - and a feature detection algorithm that is able to reliably extract the lattice and its features from noisy depth images.
  • Thumbnail Image
    Item
    Generative Landmarks
    (The Eurographics Association, 2021) Ferman, David; Bharaj, Gaurav; Bittner, Jirí and Waldner, Manuela
    We propose a general purpose approach to detect landmarks with improved temporal consistency, and personalization. Most sparse landmark detection methods rely on laborious, manually labelled landmarks, where inconsistency in annotations over a temporal volume leads to sub-optimal landmark learning. Further, high-quality landmarks with personalization is often hard to achieve. We pose landmark detection as an image translation problem. We capture two sets of unpaired marked (with paint) and unmarked videos. We then use a generative adversarial network and cyclic consistency to predict deformations of landmark templates that simulate markers on unmarked images until these images are indistinguishable from ground-truth marked images. Our novel method does not rely on manually labelled priors, is temporally consistent, and image class agnostic - face, and hand landmarks detection examples are shown.