by America Ortiz | Jun 9, 2025 | Video Processing, Visual Computing
Bridging the Gap between Diffusion Models and Universal Quantization for Image Compression In this paper, we propose a novel quantization based forward diffusion process with theoretical foundations that tackles all three aforementioned gaps. We achieve this through...
by America Ortiz | May 23, 2025 | Visual Computing
Unboxed: Geometrically and Temporally Consistent Video Outpainting In this work, we address this problem using two key ideas: 3D supported outpainting for the static regions of the images, and leveraging pre-trained video diffusion model to ensure realistic and...
by America Ortiz | May 13, 2025 | Capture, VFX, Visual Computing
Gaussian Billboards: Expressive 2D Gaussian Splatting with Textures In this work we highlight the similarity between 2D Gaussian Splatting (2DGS) and billboards from traditional computer graphics. Both use flat semitransparent 2D geometry that is positioned, oriented...
by America Ortiz | May 11, 2025 | Capture, VFX, Visual Computing
Neural Facial Deformation Transfer In this work, we first present a simple data generation strategy to automatically create a large training dataset consisting of pairs of template and target character shapes in the same expression. We then leverage this dataset...
by America Ortiz | Apr 23, 2025 | Machine Learning
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion ModelsClassifier-free guidance (CFG) improves image quality and prompt alignment in diffusion models, but high guidance scales can cause oversaturation and artifacts. In this paper, we...
