Performance is a critical challenge in mobile image processing. Given a reference imaging
pipeline, or even human-adjusted pairs of images, we seek to reproduce the enhancements …

3D visual computing data are often spatially sparse. To exploit such sparsity, people have
developed hierarchical sparse data structures, such as multi-level sparse voxel grids …

DR. JIT is a new just-in-time compiler for physically based rendering and its derivative. DR.
JIT expedites research on these topics in two ways: first, it traces high-level simulation code …

Heterogeneous many-cores are now an integral part of modern computing systems ranging
from embedding systems to supercomputers. While heterogeneous many-core design offers …

We present an approach to accelerating a wide variety of image processing operators. Our
approach uses a fully-convolutional network that is trained on input-output pairs that …

This paper introduces Tiramisu, a polyhedral framework designed to generate high
performance code for multiple platforms including multicores, GPUs, and distributed …

Cell phone cameras have small apertures, which limits the number of photons they can
gather, leading to noisy images in low light. They also have small sensor pixels, which limits …

We present a new algorithm to automatically schedule Halide programs for high-
performance image processing and deep learning. We significantly improve upon the …

Image processing pipelines combine the challenges of stencil computations and stream
programs. They are composed of large graphs of different stencil stages, as well as complex …

Program autotuning has been shown to achieve better or more portable performance in a
number of domains. However, autotuners themselves are rarely portable between projects …