Intrinsic phase-preserving networks for depth super resolution

X Chen, H Wang, J Chen, K Feng, J Liu… - Proceedings of the …, 2024 - ojs.aaai.org
Depth map super-resolution (DSR) plays an indispensable role in 3D vision. We discover an
non-trivial spectral phe-nomenon: the components of high-resolution (HR) and low …

ProFake: Detecting Deepfakes in the Wild against Quality Degradation with Progressive Quality-adaptive Learning

H Xu, Y Wang, Z Wang, Z Ba, W Liu, L **… - Proceedings of the …, 2024 - dl.acm.org
Despite the promising advances in deepfake detection on current datasets, detecting visual
deepfakes in real-world scenarios (eg, deepfake videos and live streaming on YouTube) …

Toward Tiny and High-Quality Facial Makeup with Data Amplify Learning

Q **, X Chen, M **, Y Chen, R Shi, Y Zheng… - … on Computer Vision, 2024 - Springer
Contemporary makeup approaches primarily hinge on unpaired learning paradigms, yet
they grapple with the challenges of inaccurate supervision (eg, face misalignment) and …

Beyond Privacy: Generating Privacy-Preserving Faces Supporting Robust Image Authentication

T Wang, W Wen, X **
H Shao, S Wang, Y Zhou, G Song, D He, S Qin… - ar** is becoming increasingly popular across various applications, yet
existing methods primarily focus on static images and struggle with video face swap** …

Towards Artist-Like Painting Agents with Multi-Granularity Semantic Alignment

Z Hu, Y Chen, Z Zhao, J Liu, B Ke, B Ni - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
Mainstream painting agents based on stroke-based rendering (SBR) attempt to translate
visual appearance into a sequence of vectorized painting-style strokes. Lacking a direct …

FaceShield: Defending Facial Image against Deepfake Threats

J Jeong, S In, S Kim, H Shin, J Jeong, SH Yoon… - ar** Guided by 3d Modeling
W Zhou, D Chen, J Liao, J Zhang… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Face manipulation has ignited the interests of both academia and industry in very recent
years. Existing face manipulation methods can be roughly categorized into two types: face …

Text To Stealthy Adversarial Face Masks

B Lewis, T Moyse, J Parkinson, E Telford, C Whitfield… - openreview.net
Recent studies have demonstrated that modern facial recognition systems, which are based
on deep neural networks, are vulnerable to adversarial attacks, including the use of …