search

fangchangma / self-supervised-depth-completion

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"
MIT License
623 stars 135 forks source link

Use Stereo Pair Instead of Temporal Pair for Self-Supervised Training? #54

Open SwagJ opened 3 years ago

SwagJ commented 3 years ago

Hi @fangchangma,

Thank you for your impressive work. I just have one question regarding to your training setting. In the paper, you used photometric consistency between current frame and next frame as the cue for self-supervised training. But following similar idea, if using a stereo pair can accomplish such supervision as well by maintaining the photometric consistency between left & right image, right? Have you try training in such way? I think it is computationally cheaper. I am looking forward to your reply.

Best,