Depth Anything V2 This work presents Depth Anything V2. Without pursuing fancy techniques, we aim to reveal crucial findings to pave the way towards building a powerful monocular depth estimation model. Notably, compared with V1, this version produces much finer and more

robust depth predictions through three key practices: 1) replacing all labeled real images with synthetic images, 2) scaling up the capacity of our teacher model, and 3) teaching student models via the bridge of large-scale pseudo-labeled real images. Compared with the

latest models built on Stable Diffusion, our models are significantly more efficient (more than 10x faster) and more accurate. We offer models of different scales (ranging from 25M to 1.3B params) to support extensive scenarios. Benefiting from their strong generalization

capability, we fine-tune them with metric depth labels to obtain our metric depth models. In addition to our models, considering the limited diversity and frequent noise in current test

sets, we construct a versatile evaluation benchmark with precise annotations and diverse scenes to facilitate future research.

paper page:

daily papers:

Still waiting for the transformers pipeline instead of a git clone huggingface repo install in my project 😅 Results are awesome for DAv2 !!

@oleg__chomp 👀👀

great

Holy shit this is awesome. Are the rgb values directly proportional to the distance to the camera or are they relative to other elements within the scene? i.e. will anything 1 ft away from the camera always be the same shade of red across different scenes?