With the rapid growth in deepfake video content, we re-quire improved and generalizable methods to detect them. Most existing detection methods either use uni-modal cues or rely on supervised training to capture the dissonance be-tween the audio and visual modalities. While the former disregards the audio-visual correspondences entirely, the lat-ter predominantly focuses on discerning audio-visual cues within the training corpus, thereby potentially overlooking correspondences that can help detect unseen deepfakes. We present Audio- Visual Feature Fusion (AVFF), a two-stage cross-modal learning method that explicitly captures the correspondence between the audio and visual modalities for improved deepfake detection. The first stage pursues representation learning via self-supervision on real videos to capture the intrinsic audio-visual correspondences. To extract rich cross-modal representations, we use contrastive learning and autoencoding objectives, and introduce a novel audio-visual complementary masking and feature fusion strategy. The learned representations are tuned in the second stage, where deepfake classification is pursued via super-vised learning on both real and fake videos. Extensive exper-iments and analysis suggest that our novel representation learning paradigm is highly discriminative in nature. We report 98.6% accuracy and 99.1% AUC on the FakeAVCeleb dataset, outperforming the current audio-visual state-of-the-art by 14.9% and 9.9%, respectively.

Recent research on one-shot face re-enactment has progressively overcome the low-resolution constraint with the help of StyleGAN’s high-fidelity portrait generation. However, such approaches rely on explicit 2D/3D structural priors for guidance and/or use flow-based warping which constrain their performance. Moreover, existing methods are sensitive (not robust) to the source frame’s facial expressions and head pose, even though ideally only the identity of the source frame should have an effect. Addressing these limitations, we propose a novel framework exploiting the implicit 3D prior and inherent latent properties of StyleGAN2 to facilitate one-shot face re-enactment at 10242(1) with zero dependencies on explicit structural priors, (2) accommodating attribute edits, and (3) robust to diverse facial expressions and head poses of the source frame. We train an encoder using a self-supervised approach to decompose the identity and facial deformation of a portrait image within the pre-trained StyleGAN2’s predefined latent spaces itself (automatically facilitating (1) and (2)). The decomposed identity latent of the source and the facial deformation latents of the driving sequence are used to generate re-enacted frames using the StyleGAN2 generator. Additionally, to improve the identity reconstruction and to enable seamless transfer of driving motion, we propose a novel approach, Cyclic Manifold Adjustment. We perform extensive qualitative and quantitative analyses which demonstrate the superiority of the proposed approach against state-of-the-art methods. Project page: https://trevineoorloff.github.io/FaceVideoReenactment_HybridLatents.io/.