Research

Tero Karras

Tero Karras
Principal Research Scientist
Tero Karras's picture
Bio:

Tero Karras is a principal research scientist at NVIDIA Research, which he joined in 2009. His research interests include machine learning for content creation, real time ray tracing, GPU computing, and parallel algorithms. He has had a pivotal role in NVIDIA's ray tracing research, especially related to efficient construction of acceleration structures.

Research Interests:

Machine learning for content creation, Real time ray tracing, GPU computing, parallel algorithms

Publications:
Audio-Driven Facial Animation by Joint End-to-End Learning of Pose and Emotion
Facial Performance Capture with Deep Neural Networks
Apex Point Map for Constant-Time Bounding Plane Approximation
Gradient-Domain Metropolis Light Transport
Megakernels Considered Harmful: Wavefront Path Tracing on GPUs
On Quality Metrics of Bounding Volume Hierarchies
Fast Parallel Construction of High-Quality Bounding Volume Hierarchies
Understanding the Efficiency of Ray Traversal on GPUs - Kepler and Fermi Addendum
Maximizing Parallelism in the Construction of BVHs, Octrees, and k-d Trees
Improved Dual-Space Bounds for Simultaneous Motion and Defocus Blur
Efficient Triangle Coverage Tests for Stochastic Rasterization
Clipless Dual-Space Bounds for Faster Stochastic Rasterization
High-Performance Software Rasterization on GPUs
Stratified Sampling for Stochastic Transparency
Architecture Considerations for Tracing Incoherent Rays
Two Methods for Fast Ray-Cast Ambient Occlusion
Efficient Sparse Voxel Octrees - Analysis, Extensions, and Implementation
Efficient Sparse Voxel Octrees