no code implementations • 8 Mar 2021 • Qianyu Feng, Yawei Luo, Keyang Luo, Yi Yang
To generalize the model towards a real scenario, we propose to fulfill several aspects: (1) Look: visually incorporate spatial structure from the single view to enhance the expressiveness of representation; (2) Cast: perceptually align the 2D image features to the 3D shape priors with cross-modal semantic contrastive mapping; (3) Mold: reconstruct stereo-shape of target by transforming embeddings into the desired manifold.
no code implementations • CVPR 2020 • Keyang Luo, Tao Guan, Lili Ju, Yuesong Wang, Zhuo Chen, Yawei Luo
Multi-view stereo is a crucial task in computer vision, that requires accurate and robust photo-consistency among input images for depth estimation.
no code implementations • ICCV 2019 • Keyang Luo, Tao Guan, Lili Ju, Haipeng Huang, Yawei Luo
Learning-based methods are demonstrating their strong competitiveness in estimating depth for multi-view stereo reconstruction in recent years.