3 papers
cs.CV2026
Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians
Melonie de Almeida, Daniela Ivanova, Tong Shi +2
Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent…
cs.CV2026
Neural 3D Reconstruction of Planetary Surfaces from Descent-Phase Wide-Angle Imagery
Melonie de Almeida, George Brydon, Divya M. Persaud +2
Digital elevation modeling of planetary surfaces is essential for studying past and ongoing geological processes. Wide-angle imagery acquired during spacecraft descent promises to…
cs.CV2026
Splat-Portrait: Generalizing Talking Heads with Gaussian Splatting
Tong Shi, Melonie de Almeida, Daniela Ivanova +2
Talking Head Generation aims at synthesizing natural-looking talking videos from speech and a single portrait image. Previous 3D talking head generation methods have relied on doma…