Tatiana Shpilevaya
Papers
1
Total Citations
5
H-Index
1
About
Tatiana Shpilevaya is a researcher at the intersection of computer graphics, non-photorealistic rendering (NPR), and robotics, with a focus on algorithms that emulate human artistic techniques. Her most cited work, "Comparing Neural Style Transfer and Gradient-Based Algorithms in Brushstroke Rendering Tasks" (2023, 5 citations), addresses a critical challenge in NPR: generating explicit, physically plausible brushstrokes for both high-fidelity painting imitation and robotic art creation. By systematically evaluating neural style transfer against gradient-based optimization methods, Shpilevaya provides a benchmark for understanding trade-offs between aesthetic quality and computational efficiency in stroke-based rendering. Her contributions extend beyond theory, offering practical insights for controlling artistically skilled robots—a field with applications in digital art, cultural heritage preservation, and human-robot collaboration. While her citation count is modest, the work’s novelty lies in bridging deep learning with traditional heuristics, laying groundwork for more expressive and controllable NPR systems. Shpilevaya’s research is particularly valuable for students and engineers exploring how AI can replicate the nuanced, tactile qualities of human painting, making her a rising voice in computational creativity and robotic artistry.
Research Focus
Key Achievements
Top Papers
- 1