Search Results for author:
Found 3 papers, 1 papers with code
MotionPro: A Precise Motion Controller for Image-to-Video Generation
Modern approaches typically rely on large Gaussian kernels to extend motion trajectories as condition without explicitly defining movement region, leading to coarse motion control and failing to disentangle object and camera moving.
Validating Deep Learning Weather Forecast Models on Recent High-Impact Extreme Events
To address these issues, we compare ML weather prediction models (GraphCast, PanguWeather, and FourCastNet) and ECMWF's high-resolution forecast system (HRES) in three case studies: the 2021 Pacific Northwest heatwave, the 2023 South Asian humid heatwave, and the North American winter storm in 2021.
TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models
Next, TRIP executes a residual-like dual-path scheme for noise prediction: 1) a shortcut path that directly takes image noise prior as the reference noise of each frame to amplify the alignment between the first frame and subsequent frames; 2) a residual path that employs 3D-UNet over noised video and static image latent codes to enable inter-frame relational reasoning, thereby easing the learning of the residual noise for each frame.
