Synthesizing Obama

By Supasorn Suwajanakorn, S. M. Seitz, Ira Kemelmacher-Shlizerman. ACM Transactions on Graphics, 2017

571 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/7aa88dafb5d5fd5645c0ada2539e9eaf5b2fe949

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Deep Audio-visual Learning: A Survey (2020, background): “[95] proposed a “teeth proxy” to improve the visual quality of teeth during generation.”
Media Forensics and DeepFakes: An Overview (2020, background): “tation map as input [36]. Image synthesis is also achievable using only a sketch [37], [24] or a text description [27]. Likewise, the face of a person can be animated based on an audio input sequence [38], [39]. More often, the manipulation modiﬁes existing images or videos. A well-known example is ”
State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications (2018, background): “Recent publications like Face2Face [TZS ∗ 16a] and Synthesizing Obama [SSKS17] have also raised questions about ethical and safety issues.”
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection (2018, background): “Nowadays, we can generate entirely synthetic faces [9, 24], even at very high-resolutions [22], animate a subject’s face to make it express the desired emotions [5, 31], or modify facial expressions [39, 37, 23].”
paGAN (2018, unknown): “Using the weighted-median approach of [Suwajanakorn et al. 2017] produces”
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, methodology): “Despite the success of GAN-based frameworks for general image translations and manipulations [16], [21], [42], [82]– [85], and in particular for face attribute manipulations [21], [86]–[92], few databases are publicly available to the best of our knowledge.”
Attributing Fake Images to GANs: Analyzing Fingerprints in Generated Images (2018, background): “However, increasingly concerns manifest that at a certain point fake or manipulated images could become completely indistinguishable from real images [26].”
What comprises a good talking-head video generation?: A Survey and Benchmark (2020, background): “ObamaSet (Suwajanakorn et al. 2017) consists of an abundance of video footage from President Barack Obama’s weekly presidential addresses, spanning a period of eight years.”
A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild (2020, methodology): “that are either constrained by the range of identities they can generate or the range of vocabulary they are limited to. Realistic generation of talking face videos was achieved by a few recent works [19, 22] on videos of Barack Obama. They learn a mapping between the input audio 1cvit.iiit.ac.in/re”
Deepfakes: Trick or treat? (2020, unknown): “Changing a voice or imitating someone else’s voice Fraudsters used AI to mimic a CEO’s voice and then tricked a manager into transferring $243,000 (Supasorn Suwajanakorn, 2017).”
M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection (2021, background): “Recent years have witnessed the rapid development of Deepfake techniques [26, 29, 43, 52], which enable attackers to manipulate the facial area of an image and generate a forged image.”
Artificial intelligence in the creative industries: a review (2020, background): “reated mouth movement synthesis tools capable of making the subject appear to say something dierent from the actual narrative, e.g. President Barack Obama is lip-synchronized to a new audio track in [57]. More recently, DeepFaceLab [247] provided a state of the art tool for face replacement; however”
Deep learning for deepfakes creation and detection: A survey (2019, unknown): “Audio-to-Video (A2V) [68] and Text-to-Video (T2V) [142].”
Text-based editing of talking-head video (2019, background): “There is a large body of work on reconstructing facial geometry and appearance from a single image using optimization methods[Fyffe et al. 2014; Garrido et al. 2016; Ichim et al. 2015; Kemelmacher-Shlizerman 2013; Roth et al. 2017; Shi et al. 2014; Suwajanakorn et al. 2017; Thies et al. 2016].”
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (2019, background): “In principle, the results of face modeling [35] or lips modeling [31] can be stitched into an existing head video.”
Deep video portraits (2018, methodology): “Recently, many methods have been proposed for face-interior reenactment [Liu et al. 2001; Olszewski et al. 2017; Suwajanakorn et al. 2017; Thies et al. 2015, 2016; Vlasic et al. 2005].”