← Search

Dongxia Liu

2 accepted papers

2026

Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy

ICLR 2026poster

Human image animation aims to generate a video from a static reference image, guided by pose information extracted from a driving video. Existing approaches often rely on pose estimators to extract intermediate representations, but such signals are prone to errors under occlusion or complex poses. B…

Cited by 0SourcecodeScholar
2026

Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

AAAI 2026technical

Visual effects (VFX) are essential visual enhancements fundamental to modern cinematic production. Although video generation models offer cost-efficient solutions for VFX production, current methods are constrained by per-effect LoRA training, which limits generation to single effects. This fundamen

Cited by 0SourcePDFScholar