Click here to flash read.
Despite impressive performance for high-level downstream tasks,
self-supervised pre-training methods have not yet fully delivered on dense
geometric vision tasks such as stereo matching or optical flow. The application
of selfsupervised concepts, such as instance discrimination or masked image
modeling, to geometric tasks is an active area of research. In this work, we
build on the recent crossview completion framework, a variation of masked image
modeling that leverages a second view from the same scene which makes it well
suited for binocular downstream tasks. The applicability of this concept has so
far been limited in at least two ways: (a) by the difficulty of collecting
realworld image pairs -- in practice only synthetic data have been used -- and
(b) by the lack of generalization of vanilla transformers to dense downstream
tasks for which relative position is more meaningful than absolute position. We
explore three avenues of improvement: first, we introduce a method to collect
suitable real-world image pairs at large scale. Second, we experiment with
relative positional embeddings and show that they enable vision transformers to
perform substantially better. Third, we scale up vision transformer based
cross-completion architectures, which is made possible by the use of large
amounts of data. With these improvements, we show for the first time that
stateof-the-art results on stereo matching and optical flow can be reached
without using any classical task-specific techniques like correlation volume,
iterative estimation, image warping or multi-scale reasoning, thus paving the
way towards universal vision models.
No creative common's license