Rv-gan: Recurrent gan for unconditional video generation

S Gupta, A Keshari, S Das - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Generative models aiming to generate content from noise have achieved high-fidelity
synthesis for image data. However, obtaining comparable performance in the field of …

3D-aware multi-class image-to-image translation with NeRFs

S Li, J Van De Weijer, Y Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recent advances in 3D-aware generative models (3D-aware GANs) combined with Neural
Radiance Fields (NeRF) have achieved impressive results. However no prior works …

Learning temporally and semantically consistent unpaired video-to-video translation through pseudo-supervision from synthetic optical flow

K Wang, K Akash, T Misu - Proceedings of the AAAI Conference on …, 2022 - ojs.aaai.org
Unpaired video-to-video translation aims to translate videos between a source and a target
domain without the need of paired training data, making it more feasible for real …

Temporally consistent sequence-to-sequence translation of cataract surgeries

Y Frisch, M Fuchs, A Mukhopadhyay - International Journal of Computer …, 2023 - Springer
Purpose Image-to-image translation methods can address the lack of diversity in publicly
available cataract surgery data. However, applying image-to-image translation to videos …

Translation-based Video-to-Video Synthesis

P Saha, C Zhang - arxiv preprint arxiv:2404.04283, 2024 - arxiv.org
Translation-based Video Synthesis (TVS) has emerged as a vital research area in computer
vision, aiming to facilitate the transformation of videos between distinct domains while …

Cross-modal alignment and translation for missing modality action recognition

Y Park, S Woo, S Lee, MA Nugroho, C Kim - Computer Vision and Image …, 2023 - Elsevier
Multimodal data provide complementary information on the same context, leading to
performance improvement in video action recognition. However, in reality, not all modalities …

Temporally Consistent Unpaired Multi-domain Video Translation by Contrastive Learning

R Fan, Q Sun, R **a, Y Tang - 2024 International Joint …, 2024 - ieeexplore.ieee.org
Unpaired multi-domain video-to-video translation is an attractive solution for diverse video
translation, which has to deal with not only unpaired data but also spatio-temporal …

Addressing the Domain Shift in Computer Vision for Boiling Crisis Detection

F Al-Hindawi - 2024 - search.proquest.com
Boiling crisis detection, also known as critical heat flux (CHF), represents a formidable
challenge in thermal engineering and is of paramount importance to various industrial …

System and method for learning temporally consistent video synthesis using fake optical flow

T Misu, K Akash, K Wang - US Patent App. 17/500,176, 2022 - Google Patents
BACKGROUND [0002] There are existing methods that may estimate opti cal flow. Such
methods utilize expensive pre-trained datasets that require management and updating. In …