Consistent Depth of Moving Objects in Video
Autor: | Zhang, Zhoutong, Cole, Forrester, Tucker, Richard, Freeman, William T., Dekel, Tali |
---|---|
Rok vydání: | 2021 |
Předmět: | |
Zdroj: | ACM Trans. Graph., Vol. 40, No. 4, Article 148, August 2021 |
Druh dokumentu: | Working Paper |
DOI: | 10.1145/3450626.3459871 |
Popis: | We present a method to estimate depth of a dynamic scene, containing arbitrary moving objects, from an ordinary video captured with a moving camera. We seek a geometrically and temporally consistent solution to this underconstrained problem: the depth predictions of corresponding points across frames should induce plausible, smooth motion in 3D. We formulate this objective in a new test-time training framework where a depth-prediction CNN is trained in tandem with an auxiliary scene-flow prediction MLP over the entire input video. By recursively unrolling the scene-flow prediction MLP over varying time steps, we compute both short-range scene flow to impose local smooth motion priors directly in 3D, and long-range scene flow to impose multi-view consistency constraints with wide baselines. We demonstrate accurate and temporally coherent results on a variety of challenging videos containing diverse moving objects (pets, people, cars), as well as camera motion. Our depth maps give rise to a number of depth-and-motion aware video editing effects such as object and lighting insertion. Comment: Published at SIGGRAPH 2021 |
Databáze: | arXiv |
Externí odkaz: |