no code implementations • 13 Mar 2024 • Tuomas Varanka, Tapani Toivonen, Soumya Tripathy, Guoying Zhao, Erman Acar
In our approach a restoration model is personalized using a few images of the identity, leading to tailored restoration with respect to the identity while retaining fine-grained details.
1 code implementation • 5 Feb 2024 • Shanshan Wang, Soumya Tripathy, Toni Heittola, Annamaria Mesaros
In Self-Supervised Learning (SSL), Audio-Visual Correspondence (AVC) is a popular task to learn deep audio and video features from large unlabeled datasets.
1 code implementation • 10 Nov 2022 • Shanshan Wang, Soumya Tripathy, Annamaria Mesaros
To improve the discriminative ability of feature embeddings in SSL, we propose a new loss function called Angular Contrastive Loss (ACL), a linear combination of angular margin and contrastive loss.
no code implementations • 7 Apr 2021 • Soumya Tripathy, Juho Kannala, Esa Rahtu
Image reenactment is a task where the target object in the source image imitates the motion represented in the driving image.
no code implementations • 9 Nov 2020 • Soumya Tripathy, Juho Kannala, Esa Rahtu
However, if the identity differs, the driving facial structures leak to the output distorting the reenactment result.
1 code implementation • 3 Apr 2019 • Soumya Tripathy, Juho Kannala, Esa Rahtu
This paper presents a generic face animator that is able to control the pose and expressions of a given face image.
1 code implementation • 8 May 2018 • Soumya Tripathy, Juho Kannala, Esa Rahtu
In this paper, we propose a new general purpose image-to-image translation model that is able to utilize both paired and unpaired training data simultaneously.