Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation
CVPR Workshops, pp. 0-0, 2019.
The field of self-supervised monocular depth estimation has seen huge advancements in recent years. Most methods assume stereo data is available during training but usually under-utilize it and only treat it as a reference signal. We propose a novel self-supervised approach which uses both left and right images equally during training, bu...More
PPT (Upload PPT)