Skip to main content

and
  1. No Access

    Article

    Attention Unet++ for lightweight depth estimation from sparse depth samples and a single RGB image

    Depth estimation from a single RGB image with sparse depth measurements has already been proved to be an effective way of predicting dense and high-precision depth maps. However, most of its networks are based...

    Tao Zhao, Shuguo Pan, Wang Gao, Chao Sheng, Yingchun Sun in The Visual Computer (2022)

  2. No Access

    Chapter and Conference Paper

    Towards Accurate Network Quantization with Equivalent Smooth Regularizer

    Neural network quantization techniques have been a prevailing way to reduce the inference time and storage cost of full-precision models for mobile devices. However, they still suffer from accuracy degradation...

    Kirill Solodskikh, Vladimir Chikin, Ruslan Aydarkhanov in Computer Vision – ECCV 2022 (2022)