Gururaj Gopal Putraya

Fast EPI based depth for plenoptic cameras

We present a depth estimation method for light field cameras by making use of Epipolar Plane Image (EPI) representations of the microlens sub images. Light field raw image structure has several sub images and generally depth is estimated using multi baseline techniques or object labeling schemes. Both these approaches are quite complex. EPI representation of the sub images when applied to the multi-baseline framework provides outputs comparable to that of the multi-baseline approach along with significant reduction in complexity (50%). Fast depth estimation will become an important requirement as plenoptic cameras gets into the main stream. The proposed method has been tested on a couple of datasets captured with different light field camera setups and was found to perform as well as the multi-baseline approach in terms of quality of the depth map generated but taking only half of the computational time.

Pixel resolution plenoptic disparity using cost aggregation

We present a hierarchical method for estimating pixel resolution disparity from a raw Plenoptic 2.0 light field capture. Accurate pixel resolution disparity is essential for reconstruction of a high quality conventional image, and also for various applications that depend on disparity, like object segmentation, bokeh etc. Most light field disparity estimation methods in the literature compute disparity at microlens resolution, which is much lower than the resolution of the final reconstructed image. The algorithms that do compute pixel resolution disparity are iterative, making them computationally complex. The proposed method computes disparity hierarchically, in two steps. In the first step, microlens resolution disparity is computed, using which a conventional high resolution image is reconstructed. In the second step, globally smooth and accurate disparity is estimated at a pixel level on the reconstructed image, using the computationally efficient minimum spanning tree based cost aggregation approach. Experimental results demonstrate that the accuracy of the disparity maps generated by our method, in comparison to the Multibaseline and Raytrix algorithms is superior.

Subspace based disparity estimation for plenoptic cameras

We present a subspace based disparity estimation technique for plenoptic 2.0 lightfield cameras. The raw lightfield image contains a micro-image for every lens in the micro-lens array. The disparity of a scene point is typically estimated using multi-baseline approach. The multi-baseline approach necessitates that a focussed copy of a patch is present in at least one of the neighboring micro-images. This requirement limits the range over which the disparity can be reliably estimated. We propose a subspace based technique for disparity estimation wherein a subspace for every disparity is learnt separately, and the learnt subspaces are subsequently used for estimating the disparity of any micro-image. We estimate the disparities for the images captured using Raytrix R11 camera and compare the results with (a) estimates obtained from the multi-baseline approach, and (b) manufacturer provided disparity maps. Comparisons show that the disparity maps estimated by the proposed technique are superior. In addition, the proposed technique allows for extending the range over which the disparity can be estimated.