3 papers
cs.CV2026
Ctrl&Shift: High-Quality Geometry-Aware Object Manipulation in Visual Generation
Penghui Ruan, Bojia Zi, Xianbiao Qi +5
Object-level manipulation, relocating or reorienting objects in images or videos while preserving scene realism, is central to film post-production, AR, and creative editing. Yet e…
cs.CV2025
SparseDiT: Token Sparsification for Efficient Diffusion Transformer
Shuning Chang, Pichao Wang, Jiasheng Tang +2
Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the qu…
cs.CV2024
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
Penghui Ruan, Pichao Wang, Divya Saxena +2
Despite advancements in Text-to-Video (T2V) generation, producing videos with realistic motion remains challenging. Current models often yield static or minimally dynamic outputs,…