Wenbo Li‘s paper ‘MAT: Mask-Aware Transformer for Large Hole Image Inpainting‘ was selected in the CVPR 2022 Best Paper Finalists. This paper presents a novel transformer-based model for large hole inpainting, which unifies the merits of transformers and convolutions to efficiently process high-resolution images. The careful design of each component of the framework guarantees the high fidelity and diversity of recovered images. Specifically, an inpainting-oriented transformer block was customized, where the attention module aggregates non-local information only from partial valid tokens, indicated by a dynamic mask. Extensive experiments demonstrate the state-of-the-art performance of the new model on multiple benchmark datasets.
Mr. Li is supervised by Prof. Leo Jia. His primary research interests lie in low-level computer vision, including super-resolution, denoising, inpainting, etc. He has published over 10 papers at top-tier computer vision conferences, one of which was selected in the CVPR 2022 Best Paper Finalists. He also serves as a reviewer for TPAMI, NeurIPS, CVPR, ICCV, ECCV, AAAI, etc.
The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) is the premier annual computer vision event comprising the main conference and several co-located workshops and short courses. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers.