3D Content
3D content generation and manipulation are active research areas aiming to create realistic and versatile three-dimensional models and scenes. Current efforts focus on improving real-time rendering, AI-assisted collaborative creation, and style transfer using techniques like Gaussian splatting and diffusion models, often incorporating 3D priors or leveraging foundation models like Segment Anything Model. These advancements are significant for various applications, including virtual and augmented reality, computer-aided design, and medical imaging, by enabling more efficient and accurate 3D content creation and analysis.
Papers
3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation
Ho Hin Lee, Shunxing Bao, Yuankai Huo, Bennett A. Landman
DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment
Mariia Gladkova, Nikita Korobov, Nikolaus Demmel, Aljoša Ošep, Laura Leal-Taixé, Daniel Cremers