5 papers
ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing
Caiyi Sun, Yujing Sun, Siu-Ming Yiu
Recent generic reference-based image generation models natively support multiple conditions by concatenating all reference image and text tokens into a joint sequence processed by…
UniBioTransfer: A Unified Framework for Multiple Biometrics Transfer
Caiyi Sun, Yujing Sun, Xiangyu Li +5
Deepface generation has traditionally followed a task-driven paradigm, where distinct tasks (e.g., face transfer and hair transfer) are addressed by task-specific models. Neverthel…
HUMOF: Human Motion Forecasting in Interactive Social Scenes
Caiyi Sun, Yujing Sun, Xiao Han +5
Complex scenes present significant challenges for predicting human behaviour due to the abundance of interaction information, such as human-human and humanenvironment interactions.…
Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching
Yujing Sun, Caiyi Sun, Yuan Liu +2
In this paper, we present a novel generalizable object pose estimation method to determine the object pose using only one RGB image. Unlike traditional approaches that rely on inst…
Extreme Two-View Geometry From Object Poses with Diffusion Models
Yujing Sun, Caiyi Sun, Yuan Liu +2
Human has an incredible ability to effortlessly perceive the viewpoint difference between two images containing the same object, even when the viewpoint change is astonishingly vas…