5 papers
SOP^2: Transfer Learning with Scene-Oriented Prompt Pool on 3D Object Detection
Ching-Hung Cheng, Hsiu-Fu Wu, Bing-Chen Wu +3
With the rise of Large Language Models (LLMs) such as GPT-3, these models exhibit strong generalization capabilities. Through transfer learning techniques such as fine-tuning and p…
Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinement
Chia-Hern Lai, I-Hsuan Lo, Yen-Ku Yeh +2
The creation of lifelike human avatars capable of realistic pose variation and viewpoint flexibility remains a fundamental challenge in computer vision and graphics. Current approa…
UI-Styler: Ultrasound Image Style Transfer with Class-Aware Prompts for Cross-Device Diagnosis Using a Frozen Black-Box Inference Network
Nhat-Tuong Do-Tran, Ngoc-Hoang-Lam Le, Ching-Chun Huang
The appearance of ultrasound images varies across acquisition devices, causing domain shifts that degrade the performance of fixed black-box downstream inference models when reused…
TRUST: Token-dRiven Ultrasound Style Transfer for Cross-Device Adaptation
Nhat-Tuong Do-Tran, Ngoc-Hoang-Lam Le, Ian Chiu +2
Ultrasound images acquired from different devices exhibit diverse styles, resulting in decreased performance of downstream tasks. To mitigate the style gap, unpaired image-to-image…
TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views
Hsiang-Hui Hung, Huu-Phu Do, Yung-Hui Li +1
We present TimeNeRF, a generalizable neural rendering approach for rendering novel views at arbitrary viewpoints and at arbitrary times, even with few input views. For real-world a…