activity
20222026
most citedEPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

7 citations · 7 across the 4 of their papers we have counts for

collaborators
Showing 2024Show all

2 papers · 1 filter

cs.CV2024

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,…