Autonomous vehicles and robots need to operate over a wide variety of
sc...
Monocular depth estimation is scale-ambiguous, and thus requires scale
s...
A practical benefit of implicit visual representations like Neural Radia...
Differentiable volumetric rendering is a powerful paradigm for 3D
recons...
Modern computer vision has moved beyond the domain of internet photo
col...
Modern 3D computer vision leverages learning to boost geometric reasonin...
Camera calibration is integral to robotics and computer vision algorithm...
Self-supervised monocular depth and ego-motion estimation is a promising...
Self-supervised learning has emerged as a powerful tool for depth and
eg...
We introduce DIODE, a dataset that contains thousands of diverse high
re...
State-of-the-art algorithms for many semantic visual tasks are based on ...