Vector clip-art images consist of regions bounded by a network of vector curves. Users often wish to reshape, or rescale, existing clip-art images by changing the locations, proportions, or scales of different image elements. When reshaping images depicting synthetic content they seek to preserve global and local structures.

Many applications ranging from quasi-Monte Carlo integration over optimal control to neural networks benefit from high-dimensional, highly uniform samples. In the case of computer graphics,  and more particularly in rendering, despite the need for uniformity, several sub-problems expose a low-dimensional structure. In this context, mastering sampling uniformity over projections while preserving high-dimensional uniformity has been intrinsically challenging. This difficulty may explain the relatively small number of mathematical constructions for such samplers. We pr

Unprecedented image quality in holographic near-eye displays with a fast phase-only SLM 

Ultra-thin (2.5 mm) glasses-form factor VR display supporting 3D holographic images 

As scenes become ever more complex and real-time applications embrace ray tracing, path sampling algorithms that maximize quality at low sample counts become vital.

We aim to ask and answer an essential question “how quickly do we react after observing a displayed visual target?” To this end, we present psychophysical studies that characterize the remarkable disconnect between human saccadic behaviors and spatial visual acuity. Building on the results of our studies, we develop a perceptual model to predict temporal gaze behavior, particularly saccadic latency, as a function of the statistics of a displayed image.

Despite billions of hours of play and copious discussion online, mouse sensitivity recommendations for first-person targeting tasks vary by a factor of 10x or more and remain an active topic of debate in both competitive and recreational gaming communities.Inspired by previous academic literature in pointer-based gain optimization, we conduct the first user study of mouse sensitivity in first person targeting tasks, reporting a statistically significant range of optimal values in both task completion time and throughput. Due to inherent incompatibility (i.e., lack of convert-ability) b

Using technology in esports can address historical disparities such as gender, age, and ableism in professional play. To advance the field, it is important to focus on interdisciplinary esports research networks and communities. Topics relevant for future HCI/esports research include competitive physical sports versus esports, spectatorship, and inclusion.

Volumetric representations are popular in inverse rendering because they have a simple parameterization, are smoothly varying, and transparently handle topology changes. However, incorporating the full volumetric transport of light is costly and challenging, often leading practitioners to implement simplified models, such as purely emissive and absorbing volumes with "baked" lighting. One such challenge is the efficient estimation of the gradients of the volume's appearance with respect to its scattering and absorption parameters. We show that the straightforward approach—dif

Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations: a small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for