no code implementations • 19 Aug 2021 • Shun Yao, Fei Yang, Yongmei Cheng, Mikhail G. Mozerov
We propose Local Geometry Code Learning (LGCL), a model that improves the original DeepSDF results by learning from a local shape geometry of the full 3D shape.
1 code implementation • CVPR 2021 • Fei Yang, Luis Herranz, Yongmei Cheng, Mikhail G. Mozerov
Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance.
no code implementations • 6 May 2019 • Mikhail G. Mozerov, Fei Yang, Joost Van de Weijer
In this paper, we adapt the geodesic distance-based recursive filter to the sparse data interpolation problem.
no code implementations • 12 Jan 2019 • Mikhail G. Mozerov, Joost Van de Weijer
We show that the OVOD approach considerably improves results for cost augmentation and energy minimization techniques in comparison with the standard one-view affinity space implementation.
no code implementations • 29 Oct 2014 • Mikhail G. Mozerov
This paper presents a novel extended dynamic programming approach for energy minimization (EDP) to solve the correspondence problem for stereo and motion.