12 papers
MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints
Thinh Phan, Hao Vo, Khoa Vo +3
The core challenge in multi-view pedestrian detection (MVPD) lies in effective aggregation of visual features from different viewpoints for robust occlusion reasoning. Recent appro…
Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers
Anh Nguyen, Ngan Nguyen, Duc Vu +11
Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: Teacher and Student must inha…
SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion
Huy Duong, Trong-Tung Nguyen, Cuong Pham +3
Diffusion models have achieved remarkable success in high-quality image synthesis, sparking interest in image-guided generation tasks such as subject-driven image personalization.…
InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting
Duc Vu, Kien Nguyen, Trong-Tung Nguyen +5
Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text-to-image models offer faster generatio…
BluRef: Unsupervised Image Deblurring with Dense-Matching References
Bang-Dang Pham, Anh Tran, Cuong Pham +1
This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effect…
TornadoNet: Real-Time Building Damage Detection with Ordinal Supervision
Robinson Umeike, Cuong Pham, Ryan Hausen +8
We present TornadoNet, a comprehensive benchmark for automated street-level building damage assessment evaluating how modern real-time object detection architectures and ordinal-aw…