Sökning: "Texturer"
Visar resultat 1 - 5 av 67 uppsatser innehållade ordet Texturer.
1. Procedurellt genererade eldbollar är framtiden av magi : Utveckling av metoder för procedurell generering av förmågor till MOBA-spel
Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskapSammanfattning : Procedurell generering är ofta använt av spelutvecklare i dagens moderna samhälle. Generellt så används procedurell generering mestadels till att generera terräng och texturer, vilket är ett välutforskat område, men det är bara början till vad det kan användas till. LÄS MER
2. Procedural generation and weathering of building facades : Replicating shape and distribution of wear-and-tear on real-world building facades
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Manual modeling of building facades can be a cumbersome process. Instead, procedurally modeling building facades is a practical and quick way to achieve impressive visual results. This paper presents a method for prototyping 2D facades existing in a 3d environment, with the inclusion of shading-based procedural wear-and-tear. LÄS MER
3. 3D Texture Synthesis Using Graph Neural Cellular Automata
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In recent years, texture synthesis has been a heated topic in computer graphics, and the development of advanced algorithms for generating high-quality 3D textures is an area of active research. A recently proposed model, Neural Cellular Automata, can synthesize realistic 2D texture images or videos. LÄS MER
4. Text-Driven Fashion Image Manipulation with GANs : A case study in full-body human image manipulation in fashion
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Language-based fashion image editing has promising applications in design, sustainability, and art. However, it is considered a challenging problem in computer vision and graphics. The diversity of human poses and the complexity of clothing shapes and textures make the editing problem difficult. LÄS MER
5. Humans in the wild : NeRFs for Dynamic Scenes Modeling from In-the-Wild Monocular Videos with Humans
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Recent advancements in computer vision have led to the emergence of Neural Radiance Fields (NeRFs), a powerful tool for reconstructing photorealistic 3D scenes, even in dynamic settings. However, these methods struggle when dealing with human subjects, especially when the subject is partially obscured or not completely observable, resulting in inaccurate reconstructions of geometries and textures. LÄS MER