Haibin Huang

SwiftVR achieves real-time 1080p video restoration on consumer GPUs, a first in the field, while maintaining high perceptual quality and low inference costs.

Imagine turning any single-view video into a fully explorable, dynamic 4D scene – this paper gets us closer with a novel diffusion-based approach and a new large-scale dataset.

Stop blasting your diffusion models with a single, static reward signal: fine-grained credit assignment across denoising steps and objectives unlocks better image and video generation.

Motion editing and retargeting are two sides of the same generative coin, solvable with a single conditional flow model.

Achieve superior scene-consistent video generation by training a model to iteratively estimate geometry and render novel views, using geometry as context.