Abstract We explore creating smooth transitions between videos of different scenes. As in traditional image morphing, good spatial correspondence is crucial to prevent ghosting, especially at silhouettes. Video morphing presents added challenges. Because motions are often unsynchronized, temporal alignment is also necessary. Applying morphing to individual frames leads to discontinuities, so temporal coherence must be considered. Our approach is to optimize a full spatiotemporal mapping between the two videos. We reduce tedious interactions by letting the optimization derive the fine‐scale map given only sparse user‐specified constraints. For robustness, the optimization objective examines structural similarity of the video content. We demonstrate the approach on a variety of videos, obtaining results using few explicit correspondences.

We present a massively parallel vector graphics rendering pipeline that is divided into two components. The preprocessing component builds a novel adaptive acceleration data structure, the shortcut tree . Tree construction is efficient and parallel at the segment level, enabling dynamic vector graphics. The tree allows efficient random access to the color of individual samples, so the graphics can be warped for special effects. The rendering component processes all samples and pixels in parallel. It was optimized for wide antialiasing filters and a large number of samples per pixel to generate sharp, noise-free images. Our sample scheduler allows pixels with overlapping antialiasing filters to share samples. It groups together samples that can be computed with the same vector operations using little memory or bandwidth. The pipeline is feature-rich, supporting multiple layers of filled paths, each defined by curved outlines (with linear, rational quadratic, and integral cubic Bézier segments), clipped against other paths, and painted with semi-transparent colors, gradients, or textures. We demonstrate renderings of complex vector graphics in state-of-the-art quality and performance. Finally, we provide full source-code for our implementation as well as the input data used in the paper.

The main challenge in achieving good image morphs is to create a map that aligns corresponding image elements. Our aim is to help automate this often tedious task. We compute the map by optimizing the compatibility of corresponding warped image neighborhoods using an adaptation of structural similarity. The optimization is regularized by a thin-plate spline and may be guided by a few user-drawn points. We parameterize the map over a halfway domain and show that this representation offers many benefits. The map is able to treat the image pair symmetrically, model simple occlusions continuously, span partially overlapping images, and define extrapolated correspondences. Moreover, it enables direct evaluation of the morph in a pixel shader without mesh rasterization. We improve the morphs by optimizing quadratic motion paths and by seamlessly extending content beyond the image boundaries. We parallelize the algorithm on a GPU to achieve a responsive interface and demonstrate challenging morphs obtained with little effort.

No abstract available.

Image processing operations like blurring, inverse convolution, and summed-area tables are often computed efficiently as a sequence of 1D recursive filters. While much research has explored parallel recursive filtering, prior techniques do not optimize across the entire filter sequence. Typically, a separate filter (or often a causal-anticausal filter pair) is required in each dimension. Computing these filter passes independently results in significant traffic to global memory, creating a bottleneck in GPU systems. We present a new algorithmic framework for parallel evaluation. It partitions the image into 2D blocks, with a small band of additional data buffered along each block perimeter. We show that these perimeter bands are sufficient to accumulate the effects of the successive filters. A remarkable result is that the image data is read only twice and written just once, independent of image size, and thus total memory bandwidth is reduced even compared to the traditional serial algorithm. We demonstrate significant speedups in GPU computation.