3D Moments from Near-Duplicate Photos
This addresses a computational photography challenge for enhancing personal photo collections with 3D effects, but it is incremental as it builds on existing layered depth and scene flow methods.
The paper tackles the problem of generating smooth, photorealistic videos from pairs of near-duplicate photos by interpolating scene motion and adding camera parallax, resulting in superior performance over baselines on public datasets and in-the-wild photos.
We introduce 3D Moments, a new computational photography effect. As input we take a pair of near-duplicate photos, i.e., photos of moving subjects from similar viewpoints, common in people's photo collections. As output, we produce a video that smoothly interpolates the scene motion from the first photo to the second, while also producing camera motion with parallax that gives a heightened sense of 3D. To achieve this effect, we represent the scene as a pair of feature-based layered depth images augmented with scene flow. This representation enables motion interpolation along with independent control of the camera viewpoint. Our system produces photorealistic space-time videos with motion parallax and scene dynamics, while plausibly recovering regions occluded in the original views. We conduct extensive experiments demonstrating superior performance over baselines on public datasets and in-the-wild photos. Project page: https://3d-moments.github.io/