Rainbow Group Seminars

Hanxue Liang will present his recent work BulletTimer. BulletTimer is the first motion-aware feed-forward model for real-time dynamic scene reconstruction. It takes a monocular video as input and reconstructs a 3D Gaussian Splatting (3DGS) representation at any desired timestamp in a feed-forward manner within just 150 ms...

Vision, as a symphony of physics and intelligence, encompasses two interconnected dimensions: sensing and perception. Visual sensing, grounded in physical optics, harnesses computational intelligence to enhance light capture. Visual perception, driven by intelligence, is now empowered by physical optics to interpret visual...

In this talk, we will start from the fundamental question of what is, how to measure, how to improve the generalization ability of deep neural networks, especially on the out-of-distribution generalization ability, where the test data distribution differs from the training data distribution. Then, we will demonstrate how...

Speaker bio: Shelly Levy-Tzedek is an associate professor and the director of the Cognition, Aging & Rehabilitation Laboratory at Ben Gurion University. Prof. Levy-Tzedek completed her undergraduate studies, summa cum laude, at UC Berkeley, where she won the Bioengineering departmental citation medal. At the...

The study investigates the modelling of contrast matching functions (SCMF) across various luminance levels, addressing the nonlinear behaviour of the human visual system in perceiving suprathreshold contrasts. Using a comprehensive dataset of contrast matching experiments involving younger and older observers, the research...

Recent developments in computer graphics, and particularly within predictive rendering, enable highly realistic simulations of object appearances. Though physically-based reflectance (PBR) models offer widespread utility, measured material reflectance data yields significantly superior accuracy through the direct empirical...

Near-eye volumetric displays, showing multiple focal planes, require knowledge of the accurate position of the nodal point of the eye to correctly render a 3D scene. This is because pixels seen through multiple planes must be accurately aligned with the eye’s visual axis to ensure consistency across focal planes. While...

[CANCELLED] Cameras cannot capture the same colors as those seen by the human eye because the eye and the cameras’ sensors differ in their spectral sensitivity. To obtain a plausible approximation of perceived colors, the camera’s Image Signal Processor (ISP) employs a color correction step. However, even advanced color...

In daily life, visual properties such as color and gloss are crucial for identifying and distinguishing objects around us. I will present two research projects that investigated the mechanisms of color and gloss perception using deep neural networks (DNNs). In the first project, we used DNNs to explore why we have higher...

When can we trust a data visualization to communicate the same message to different groups of people? Most visualization guidelines are untested and biased toward one designer's viewpoint. What scientific evidence can we bring to visualization, and what methods can we use to ensure that visualizations are working for...