资源论文Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation

Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation

2019-09-27 | |  182 |   60 |   0

Abstract Nowadays, the majority of state of the art monocular depth estimation techniques are based on supervised deep learning models. However, collecting RGB images with associated depth maps is a very time consuming procedure. Therefore, recent works have proposed deep architectures for addressing the monocular depth prediction task as a reconstruction problem, thus avoiding the need of collecting ground-truth depth. Following these works, we propose a novel self-supervised deep model for estimating depth maps. Our framework exploits two main strategies: refifinement via cycle-inconsistency and distillation. Specififically, fifirst a student network is trained to predict a disparity map such as to recover from a frame in a camera view the associated image in the opposite view. Then, a backward cycle network is applied to the generated image to re-synthesize back the input image, estimating the opposite disparity. A third network exploits the inconsistency between the original and the reconstructed input frame in order to output a refifined depth map. Finally, knowledge distillation is exploited, such as to transfer information from the refifinement network to the student. Our extensive experimental evaluation demonstrate the effectiveness of the proposed framework which outperforms state of the art unsupervised methods on the KITTI benchmark

上一篇:Quasi-Unsupervised Color Constancy

下一篇:Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...