Browsing by Author "Kim, Byungmoon"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Dynamic Deep Octree for High-resolution Volumetric Painting in Virtual Reality
    (The Eurographics Association and John Wiley & Sons Ltd., 2018) Kim, Yeojin; Kim, Byungmoon; Kim, Young J.; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
    With virtual reality, digital painting on 2D canvas is now being extended to 3D space. In this paper, we generalize the 2D pixel canvas to a 3D voxel canvas to allow artists to synthesize volumetric color fields. We develop a deep and dynamic octree-based painting and rendering system using both CPU and GPU to take advantage of the characteristics of both processors (CPU for octree modeling and GPU for volume rendering). On the CPU-side, we dynamically adjust an octree and incrementally update the octree to GPU with low latency without compromising the frame rates of the rendering. Our octree is balanced and uses a novel 3-neighbor connectivity for format simplicity and efficient storage, while allowing constant neighbor access time in ray casting. To further reduce the GPU-side 3-neighbor computations, we precompute a culling mask in CPU and upload it to GPU. Finally, we analyze the numerical error-propagation in ray casting through high resolution octree and present a theoretical error bound.
  • Thumbnail Image
    Item
    LPaintB: Learning to Paint from Self-Supervision
    (The Eurographics Association, 2019) Jia, Biao; Brandt, Jonathan; Mech, Radomír; Kim, Byungmoon; Manocha, Dinesh; Lee, Jehee and Theobalt, Christian and Wetzstein, Gordon
    We present a novel reinforcement learning-based natural media painting algorithm. Our goal is to reproduce a reference image using brush strokes and we encode the objective through observations. Our formulation takes into account that the distribution of the reward in the action space is sparse and training a reinforcement learning algorithm from scratch can be difficult. We present an approach that combines self-supervised learning and reinforcement learning to effectively transfer negative samples into positive ones and change the reward distribution. We demonstrate the benefits of our painting agent to reproduce reference images with brush strokes. The training phase takes about one hour and the runtime algorithm takes about 30 seconds on a GTX1080 GPU reproducing a 1000x800 image with 20,000 strokes.
  • Thumbnail Image
    Item
    Simulation of Dendritic Painting
    (The Eurographics Association and John Wiley & Sons Ltd., 2020) Canabal, José A.; Otaduy, Miguel A.; Kim, Byungmoon; Echevarria, Jose; Panozzo, Daniele and Assarsson, Ulf
    We present a new system for interactive dendritic painting. Dendritic painting is characterized by the unique and intricate branching patterns that grow from the interaction of inks, solvents and medium. Painting sessions thus become very dynamic and experimental. To achieve a compelling simulation of this painting technique we introduce a new Reaction-Diffusion model with carefully designed terms to allow natural interactions in a painting context. We include additional user control not possible in the real world to guide and constrain the growth of the patterns in expressive ways. Our multi-field model is able to capture and simulate all these complex phenomena efficiently in real time, expanding the tools available to the digital artist, while producing compelling animations for motion graphics.