Tag: graphics

Towards better color spaces

interesting that there’s still advances on better mapping colors to the human perceptual system:

In an ideal perceptual color space, the distance of 2 points in the space would correlate strongly with the perception of color difference. Put another way, all pairs separated by a “just noticeable difference” would be separated by an equal distance.

As it turns out, such a thing is no more possible than flattening an orange peel, because color perception is inherently non-euclidean. To put it simply, our eyes are more sensitive to small changes in hue than small changes in lightness or color saturation.

Even so, like map projections, it is possible to make a color space that approximates perceptual uniformity and is useful for various tasks. 1 of these, a primary focus of this blog post, is smoother gradients.

De-Aging

The Irishman Gets De-Aging Right—No Tracking Dots Necessary

he created a new type of camera rig that would allow Scorsese to shoot as he normally would while capturing all of the data the ILM team would need to make Frank Sheeran (De Niro), Jimmy Hoffa (Pacino), and Russell Bufalino (Pesci) whatever age they needed them to be

History of CGI

While it’s billed as “How Pixar Helped Win 27 of the Last 30 Oscars for Visual Effects”, this video from Wired works pretty well as a short history of computer-generated visual effects, from the Genesis visualization in Star Trek II: The Wrath of Khan to Jurassic Park’s dinosaurs to Pixar’s own Coco.

Low-light image enhancement

Imaging in low light is challenging due to low photon count and low SNR. Short-exposure images suffer from noise, while long exposure can induce blur and is often impractical. A variety of denoising, deblurring, and enhancement techniques have been proposed, but their effectiveness is limited in extreme conditions, such as video-rate imaging at night. To support the development of learning-based pipelines for low-light image processing, we introduce a dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, we develop a pipeline for processing low-light images, based on end-to-end training of a fully-convolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work.

Enhancing color vision

We present an approach that can enhance human color vision by breaking the inherent redundancy in binocular vision, providing different spectral content to each eye. This technique represents a significant enhancement of the spectral perception of typical humans, and may have applications ranging from camouflage detection and anti-counterfeiting to art and data visualization.

State of motion capture

motion capture has come a long way

We present the first end-to-end solution to create high-quality free-viewpoint video encoded as a compact data stream. Our system records performances using a dense set of RGB and IR video cameras, generates dynamic textured surfaces, and compresses these to a streamable 3D video format. 4 technical advances contribute to high fidelity and robustness: multimodal multi-view stereo fusing RGB, IR, and silhouette information; adaptive meshing guided by automatic detection of perceptually salient areas; mesh tracking to create temporally coherent subsequences; and encoding of tracked textured meshes as an MPEG video stream. Quantitative experiments demonstrate geometric accuracy, texture fidelity, and encoding efficiency. We release several datasets with calibrated inputs and processed results to foster future research.