Neural Rendering and Reenactment of Human Actor Videos
نویسندگان
چکیده
منابع مشابه
Inferring actor communities from videos
In recent years there has been a growing interest in inferring social relations amongst actors in a video using audiovisual features, co-appearance features or both. The discovered relations between actors have been used for identifying leading roles, detecting rival communities in a movie plot etc. In this paper we propose an unsupervised method which uses the video’s transcript and closed cap...
متن کاملSupplemental Material for ”Face2Face: Real-time Face Capture and Reenactment of RGB Videos”
In this document, we provide supplementary information to the method by Thies et al. [4]. More specifically, we include additional detail about our optimization framework (see Section 1 and 2), and we show further comparisons against other methods (see Section 3). We also evaluate the reconstruction error in a self-reenactment scenario. In Section 4, a list of used mathematical symbols is given...
متن کاملParallel Rendering with an Actor Model
This paper describes an application of autonomous concurrent objects (Actors) to parallel rendering. The resulting rendering system is shown to be both scalable and portable. A parallel rendering application based on Monte Carlo path tracing is constructed using programming abstractions deened by the Actor model. This application is demonstrated to scale to hundreds of computers with eeciencies...
متن کاملThe Symbiosis of Human and Semantic Technology Through the Lens of Actor-Network Theory
Background: Semantic technologies (STs) have made machine reasoning possible by providing intelligent data management methods. This capability has created new forms of interaction between humans and STs, which is called "semantic interaction." The increasing spread of this form of interaction in daily life reveals the need to identify the factors affecting it and introduce the requirements of...
متن کاملCoherent Spatiotemporal Filtering, Upsampling and Rendering of RGBZ Videos
Sophisticated video processing effects require both image and geometry information. We explore the possibility to augment a video camera with a recent infrared time-of-flight depth camera, to capture high-resolution RGB and low-resolution, noisy depth at video frame rates. To turn such a setup into a practical RGBZ video camera, we develop efficient data filtering techniques that are tailored t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Transactions on Graphics
سال: 2019
ISSN: 0730-0301,1557-7368
DOI: 10.1145/3333002