Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification

    A critical limitation of current methods based on Neural Radiance Fields (NeRF) is that they are unable to quantify the uncertainty associated with the learned appearance and geometry of the scene. This inform...

    Jianxiong Shen, Antonio Agudo, Francesc Moreno-Noguer in Computer Vision – ECCV 2022 (2022)

  2. No Access

    Chapter and Conference Paper

    Prediction Stability as a Criterion in Active Learning

    Recent breakthroughs made by deep learning rely heavily on a large number of annotated samples. To overcome this shortcoming, active learning is a possible solution. Besides the previous active learning algori...

    Junyu Liu, **ang Li, Jiqiang Zhou in Artificial Neural Networks and Machine Lea… (2020)