Mpi-sintel Optical Flow Benchmark: Supplemental Material
نویسندگان
چکیده
This Technical Report contains the supplemental material to the main report on the MPI-Sintel optical flow dataset and evaluation [1]. In particular, we provide details of the image and optical flow statistics that are mentioned in the main paper. Additionally we provide details of the initial evaluation of optical flow algorithm performance on the dataset. Additional details and the dataset itself can be found on the MPI-Sintel website:
منابع مشابه
Lessons and Insights from Creating a Synthetic Optical Flow Benchmark
With the MPI-Sintel Flow dataset, we introduce a naturalistic dataset for optical flow evaluation derived from the open source CGI movie Sintel. In contrast to the well-known Middlebury dataset, the MPI-Sintel Flow dataset contains longer and more varied sequences with image degradations such as motion blur, defocus blur, and atmospheric effects. Animators use a variety of techniques that produ...
متن کاملOcclusion Aware Unsupervised Learning of Optical Flow
It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised counterpart. Occlusion and large motion are some of the major factors that limit the current unsupervised learning of optical flow methods. In this work we int...
متن کاملOptical Flow Estimation with Channel Constancy
Large motions remain a challenge for current optical flow algorithms. Traditionally, large motions are addressed using multi-resolution representations like Gaussian pyramids. To deal with large displacements, many pyramid levels are needed and, if an object is small, it may be invisible at the highest levels. To address this we decompose images using a channel representation (CR) and replace t...
متن کاملCombinatorial Regularization of Descriptor Matching for Optical Flow Estimation
One fundamental step in many state of the art optical flow methods is the initial estimation of reliable correspondences. It is well-established to extract and match features such as HOG to handle large displacements. We propose a combinatorial refinement of the initial matching. Optimization is done in the space of affine motion, where we regularize between neighboring points and similar regio...
متن کاملOptical Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation
Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the major disadvantage of being very outlier-prone as they are not designed to find the optical flow, but the visually most similar correspondence. In this artic...
متن کامل