Open DongyangHuLi opened 11 months ago
Depth estimation results are related to focal length. Here we encode focal length information to the network by simply multiply a focal scale. For a more elegant method and the theoretical relation between focal length and depth, you may refer to this paper: Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image.
Hi, thank you for nice work! I'm confused about the 'focal_scale'. Why do we need to do this: https://github.com/weiyithu/SurroundDepth/blob/22dfecfe8fca62a38d0f682ff7bf65b41aba3cac/runer.py#L382-L383