M
Mehdi S. M. Sajjadi
Researcher at Max Planck Society
Publications - 22
Citations - 3170
Mehdi S. M. Sajjadi is an academic researcher from Max Planck Society. The author has contributed to research in topics: Convolutional neural network & Computer science. The author has an hindex of 15, co-authored 22 publications receiving 2059 citations. Previous affiliations of Mehdi S. M. Sajjadi include Google.
Papers
More filters
Proceedings ArticleDOI
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
TL;DR: In this article, a novel application of automated texture synthesis in combination with a perceptual loss focusing on creating realistic textures rather than optimizing for a pixelaccurate reproduction of ground truth images during training is proposed.
Posted Content
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
TL;DR: In this paper, a novel application of automated texture synthesis was proposed in combination with a perceptual loss focusing on creating realistic textures rather than optimizing for a pixel-accurate reproduction of ground truth images during training.
Posted Content
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
Ricardo Martin-Brualla,Noha Radwan,Mehdi S. M. Sajjadi,Jonathan T. Barron,Alexey Dosovitskiy,Daniel Duckworth +5 more
TL;DR: A learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs, and applies it to internet photo collections of famous landmarks, to demonstrate temporally consistent novel view renderings that are significantly closer to photorealism than the prior state of the art.
Proceedings ArticleDOI
Frame-Recurrent Video Super-Resolution
TL;DR: In this paper, an end-to-end trainable frame-recurrent video super-resolution framework was proposed that uses the previously inferred HR estimate to super-resolve the subsequent frame.
Proceedings Article
From Variational to Deterministic Autoencoders
TL;DR: It is shown, in a rigorous empirical study, that the proposed regularized deterministic autoencoders are able to generate samples that are comparable to, or better than, those of VAEs and more powerful alternatives when applied to images as well as to structured data such as molecules.