Essays about: "GPU Sampling"
Showing result 1 - 5 of 11 essays containing the words GPU Sampling.
-
1. Regularizing Vision-Transformers Using Gumbel-Softmax Distributions on Echocardiography Data
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This thesis introduces an novel approach to model regularization in Vision Transformers (ViTs), a category of deep learning models. It employs stochastic embedded feature selection within the context of echocardiography video analysis, specifically focusing on the EchoNet-Dynamic dataset. READ MORE
-
2. Traction Adaptive Motion Planning for Autonomous Racing
University essay from KTH/Skolan för industriell teknik och management (ITM)Abstract : Autonomous driving technology is continuously evolving at an accelerated pace. The road environment is always uncertain, which requires an evasive manoeuvre that an autonomous vehicle can take. READ MORE
-
3. GPU-Accelerated Monte Carlo Geometry Processing for Gradient-Domain Methods
University essay from Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska fakultetenAbstract : This thesis extends the utility of the Monte Carlo approach to PDE-based methods presented in the paper Monte Carlo Geometry Processing. In particular, we implement this method on the GPU using CUDA, and investigate more viable methods of estimating the source integral when solving Poisson’s equation with intricate source terms. READ MORE
-
4. Evaluating user preference when applying mipmap LOD in shadow covered textures
University essay from Blekinge Tekniska Högskola/Institutionen för datavetenskapAbstract : Background. Shadow mapping is a method that is used for generating and imitating shadows in 3D-spaces. This technique has been used in the entertainment media industry in the form of games, movies and 3D renderings of environments to create a more realistic experience for consumers. READ MORE
-
5. Comparing 3D-Clipmaps and Sparse Voxel Octrees for voxelbased cone tracing
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Voxel based cone tracing is a promising approach to approximate globalillumination for real-time applications. This technique utilizes a voxelfield approximating the original scene to retrieve the necessary radi-ance information during sampling. The simplest approach to creat-ing a voxel field is to use a 3D texture. READ MORE