A
Ayush Tewari
Researcher at Max Planck Society
Publications - Â 68
Citations - Â 4673
Ayush Tewari is an academic researcher from Max Planck Society. The author has contributed to research in topics: Computer science & Face (geometry). The author has an hindex of 20, co-authored 49 publications receiving 2381 citations.
Papers
More filters
Posted Content
PhotoApp: Photorealistic Appearance Editing of Head Portraits
Mallikarjun B R,Ayush Tewari,Abdallah Dib,Tim Weyrich,Bernd Bickel,Hans-Peter Seidel,Hanspeter Pfister,Wojciech Matusik,Louis Chevallier,Mohamed Elgharib,Christian Theobalt +10 more
TL;DR: In this paper, the camera viewpoint and scene illumination are modelled in the latent space of StyleGAN to produce high-quality photorealistic results for in-the-wild images.
Generalized metric tree arrangements and Dressians
TL;DR: In this article , the adjacency of cones in Dressian Dr ( 3 , đ ) was studied and generalized metric tree arrangements were introduced to parameterize points in the polyhedral fan structure.
Posted Content
StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN.
TL;DR: In this article, a StyleGAN network is used to generate portrait videos for the training subject, but also for any random subject which can be embedded in the StyleGAN latent space.
Proceedings Article
Exploring perceptual straightness in learned visual representations
A Harrington,Vasha DuTell,Ayush Tewari,Mark F. Hamilton,Simon Stent,Ruth Rosenholtz,William T. Freeman +6 more
TL;DR: This paper used a straightened encoding to represent the natural visual world as it evolves in time, and showed that humans have been shown to use a "straightened" encoding for representation.
Journal ArticleDOI
AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars
Mohit Mendiratta,Xingang Pan,Mohamed Elgharib,Kartik Teotia,R. MallikarjunB.,Ayush Tewari,Vladislav Golyanik,Adam Kortylewski,Christian Theobalt +8 more
TL;DR: Zhang et al. as mentioned in this paper proposed a text-to-image diffusion model for editing the appearance of a dynamic full-head avatar using neural radiance field (NeRF).