Aleksei Grigorev

Papers

Total Citations

H-Index

About

Aleksei Grigorev has made significant contributions to the field of computer vision, with a particular focus on depth estimation from monocular images. His most cited work, "Depth estimation from single monocular images using deep hybrid network" (2016, 18 citations), introduced a novel deep learning architecture that combines convolutional and recurrent neural networks to predict depth maps from single images. This approach addressed the challenging problem of inferring 3D structure from 2D inputs, offering a more efficient alternative to traditional stereo or multi-view methods. Grigorev's research demonstrates a keen ability to integrate hybrid network designs, pushing the boundaries of what is achievable with limited visual data. While his citation count reflects a specialized but impactful contribution, his work has influenced subsequent studies in autonomous navigation, augmented reality, and scene understanding. By tackling the inherent ambiguity of monocular depth perception, Grigorev has helped advance practical applications where depth sensors are unavailable or impractical. His dedication to solving fundamental vision problems marks him as a thoughtful researcher in the evolving landscape of deep learning and computer vision.