4 papers
Rasterized Steered Mixture of Experts for Efficient 2D Image Regression
Yi-Hsin Li, Mårten Sjöström, Sebastian Knorr +1
The Steered Mixture of Experts regression framework has demonstrated strong performance in image reconstruction, compression, denoising, and super-resolution. However, its high com…
Segmentation-Driven Initialization for Sparse-view 3D Gaussian Splatting
Yi-Hsin Li, Thomas Sikora, Sebastian Knorr +1
Sparse-view synthesis remains a challenging problem due to the difficulty of recovering accurate geometry and appearance from limited observations. While recent advances in 3D Gaus…
Adaptive Segmentation-Based Initialization for Steered Mixture of Experts Image Regression
Yi-Hsin Li, Sebastian Knorr, Mårten Sjöström +1
Kernel image regression methods have shown to provide excellent efficiency in many image processing task, such as image and light-field compression, Gaussian Splatting, denoising a…
Estimation of optimal encoding ladders for tiled 360° VR video in adaptive streaming systems
Cagri Ozcinar, Ana De Abreu, Sebastian Knorr +1
Given the significant industrial growth of demand for virtual reality (VR), 360° video streaming is one of the most important VR applications that require cost-optimal solutions to…