12 citations · 21 across the 5 of their papers we have counts for
5 papers
Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting
Peiyu Xu, Xin Sun, Krishna Mullia +3
Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization -- rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflect…
Neural Product Importance Sampling via Warp Composition
Joey Litalien, Miloš Hašan, Fujun Luan +2
Achieving high efficiency in modern photorealistic rendering hinges on using Monte Carlo sampling distributions that closely approximate the illumination integral estimated for eve…
Uncertainty for SVBRDF Acquisition using Frequency Analysis
Ruben Wiersma, Julien Philip, Miloš Hašan +4
This paper aims to quantify uncertainty for SVBRDF acquisition in multi-view captures. Under uncontrolled illumination and unstructured viewpoints, there is no guarantee that the o…
RNA: Relightable Neural Assets
Krishna Mullia, Fujun Luan, Xin Sun +1
High-fidelity 3D assets with materials composed of fibers (including hair), complex layered material shaders, or fine scattering geometry are ubiquitous in high-end realistic rende…
NeuMIP: Multi-Resolution Neural Materials
Alexandr Kuznetsov, Krishna Mullia, Zexiang Xu +2
We propose NeuMIP, a neural method for representing and rendering a variety of material appearances at different scales. Classical prefiltering (mipmapping) methods work well on si…