Wired Perspectives: Multi-View Wire Art Embraces Generative AI

no code implementations • 26 Nov 2023 • Zhiyu Qu, Lan Yang, Honggang Zhang, Tao Xiang, Kaiyue Pang, Yi-Zhe Song

Creating multi-view wire art (MVWA), a static 3D sculpture with diverse interpretations from different viewpoints, is a complex task even for skilled artists.

Knowledge Distillation

SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation

1 code implementation • 27 Aug 2023 • Zhiyu Qu, Tao Xiang, Yi-Zhe Song

Through this work, we hope to aspire the way we create visual content, democratise the creative process, and inspire further research in enhancing human creativity in AIGC.

SketchXAI: A First Look at Explainability for Human Sketches

no code implementations • CVPR 2023 • Zhiyu Qu, Yulia Gryaditskaya, Ke Li, Kaiyue Pang, Tao Xiang, Yi-Zhe Song

Following this, we design a simple explainability-friendly sketch encoder that accommodates the intrinsic properties of strokes: shape, location, and order.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1

Large-Scale Product Retrieval with Weakly Supervised Representation Learning

1 code implementation • 1 Aug 2022 • Xiao Han, Kam Woh Ng, Sauradip Nag, Zhiyu Qu

Large-scale weakly supervised product retrieval is a practically useful yet computationally challenging problem.

Multi-Label Classification Representation Learning +2