Waterdrop Stereo
Shaodi You, Robby T. Tan, Rei Kawakami, Yasuhiro Mukaigawa, Katsushi, Ikeuchi

TL;DR
This paper presents a novel method for depth estimation using water drops on glass, leveraging their physical properties and stereo vision principles to recover 3D shape and depth information.
Contribution
It introduces a new approach that uses water drops as fisheye lenses for depth estimation, combining physical modeling and stereo rectification.
Findings
Effective depth estimation demonstrated on real images
Water drops enable novel stereo-based depth recovery
Method allows image refocusing using water drop geometry
Abstract
This paper introduces depth estimation from water drops. The key idea is that a single water drop adhered to window glass is totally transparent and convex, and thus optically acts like a fisheye lens. If we have more than one water drop in a single image, then through each of them we can see the environment with different view points, similar to stereo. To realize this idea, we need to rectify every water drop imagery to make radially distorted planar surfaces look flat. For this rectification, we consider two physical properties of water drops: (1) A static water drop has constant volume, and its geometric convex shape is determined by the balance between the tension force and gravity. This implies that the 3D geometric shape can be obtained by minimizing the overall potential energy, which is the sum of the tension energy and the gravitational potential energy. (2) The imagery inside…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Computer Graphics and Visualization Techniques · Advanced Image and Video Retrieval Techniques
