Depth Estimation of Light Field Images by Optical Flow
نویسنده
چکیده
Light field images present a rich, compact, dataset of multiple images of a scene from slightly shifted viewpoints. I explore the use of an optical flow algorithm on light field images to estimate depth. The optical flow algorithm is simple to implement as does not require finding correspondences between images. Further, I explore the use of image priors and modern optimization techniques to form a better estimate. Where camera parameters are available, I estimate the metric depth of objects in a scene. I compare my the results of my algorithm with the results from a focal stack algorithm, the depth map produced by Lytro, and with ground truth from a synthetic dataset. The results show that it performs better than the basic depth from f algorithm, and gives comparable results to the Lytro map and ground truth in areas where the image has sufficient features.
منابع مشابه
Fast and Accurate Optical Flow based Depth Map Estimation from Light Fields
Depth map estimation is a crucial task in computer vision, and new approaches have recently emerged taking advantage of light fields, as this new imaging modality captures much more information about the angular direction of light rays compared to common approaches based on stereoscopic images or multi-view. In this paper, we propose a novel depth estimation method from light fields based on ex...
متن کاملA Multiview Light Field Camera for Scene Depth Estimation from a Single Lens
In this paper, we present a light field camera which can be viewed as a compound of a perspective lens that tansfers the ligth field on to a microlens array which acts as a multiview stereo device. The camera configuration presented here can employ parfocal lenses and benefits from the spatial resolution of focused plenoptic cameras while exhibiting low angular bias. To recover the dense depth ...
متن کاملProbabilistic Dense Depth from Monocular Images
T his proposal presents a probabilistic formalism that strives for a real time estimation of depth and 3D motion from monocular images. Given a moving camera equipped with an inertial measurement unit and capturing images of a scene with moving objects, we would like to determine, in real time, the 3D structure of the scene in the field of view of the camera as well as the different 3D motions ...
متن کاملCoded Aperture Flow
Real cameras have a limited depth of field. The resulting defocus blur is a valuable cue for estimating the depth structure of a scene. Using coded apertures, depth can be estimated from a single frame. For optical flow estimation between frames, however, the depth dependent degradation can introduce errors. These errors are most prominent when objects move relative to the focal plane of the ca...
متن کاملAdvancement in Depth Estimation for Stereo Image Pair
Many researchers invented ideas to compute depth estimation. In Hybrid Technique for Stereoscopic Depth Estimation there were some drawbacks associated with the optical flow estimation when it was done with novel disparity compensation step that the edges between the objects in disparity maps were not preserved very well which was caused in filtering step of optical flow analysis, related with ...
متن کامل