by America Ortiz | Jun 17, 2024 | Video Processing, Visual Computing
DiVAS: Video and Audio Synchronization with Dynamic Frame Rates In this paper, we study the automatic discovery of such issues. Specifically, we focus on the alignment of lip movements with spoken words, targeting realistic production scenarios which can include...
by America Ortiz | Jun 17, 2024 | Video Processing, Visual Computing
Combining Frame and GOP Embeddings for Neural Video Representation In this paper, we propose T-NeRV, a hybrid video INR that combines frame-specific embeddings with GOP-specific features, providing a lever for content-specific fine-tuning. June 17, 2024 CVPR (2024)...
by America Ortiz | Jun 7, 2024 | Capture, VFX, Visual Computing
Infinite 3D Landmarks: Improving Continuous 2D Facial Landmark Detection In this work, we examine 3 important issues in the practical use of state-of-the-art facial landmark detectors and show how a combination of specific architectural modifications can directly...
by America Ortiz | Jun 7, 2024 | Capture, VFX, Visual Computing
Stylize My Wrinkles: Bridging the Gap from Simulation to Reality In this work we aim to overcome the gap between synthetic simulation and real skin scanning, by proposing a method that can be applied to large skin regions (e.g. an entire face) with the controllability...
by America Ortiz | Jun 5, 2024 | Video Processing, Visual Computing
QUADify: Extracting Meshes with Pixel-level Details and Materials from Images In this work, we propose a method to extract regular quad-dominant meshes from posed images. More specifically, we generate a high-quality 3D model through de- composition into an easily...
