Creative Sketching
Creative sketching research explores how AI can enhance and augment the human sketching process, focusing on both the generation and interpretation of sketches. Current work leverages deep learning models, including transformers and generative adversarial networks (GANs), to improve sketch-based image retrieval, 3D model generation from sketches, and interactive sketch creation tools driven by text or other modalities. This research aims to democratize creative processes, improve human-computer interaction, and advance our understanding of visual reasoning and geometric representation, impacting fields ranging from design and robotics to data analysis and computer vision.
Papers
Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches
Ayan Kumar Bhunia, Viswanatha Reddy Gajjala, Subhadeep Koley, Rohit Kundu, Aneeshan Sain, Tao Xiang, Yi-Zhe Song
Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval
Ayan Kumar Bhunia, Subhadeep Koley, Abdullah Faiz Ur Rahman Khilji, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song