5 papers
Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
Kwanyoung Kim, Sanghyun Kim
The choice of initial noise strongly affects quality and prompt alignment in video diffusion; different seeds for the same prompt can yield drastically different results. While rec…
Few-Shot Pattern Detection via Template Matching and Regression
Eunchan Jo, Dahyun Kang, Sanghyun Kim +2
We address the problem of few-shot pattern detection, which aims to detect all instances of a given pattern, typically represented by a few exemplars, from an input image. Although…
EVT: Efficient View Transformation for Multi-Modal 3D Object Detection
Yongjin Lee, Hyeon-Mun Jeong, Yurim Jeon +1
Multi-modal sensor fusion in Bird's Eye View (BEV) representation has become the leading approach for 3D object detection. However, existing methods often rely on depth estimators…
Locality-Aware Zero-Shot Human-Object Interaction Detection
Sanghyun Kim, Deunsol Jung, Minsu Cho
Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen cate…
Burst Image Super-Resolution with Base Frame Selection
Sanghyun Kim, Min Jung Lee, Woohyeok Kim +4
Burst image super-resolution has been a topic of active research in recent years due to its ability to obtain a high-resolution image by using complementary information between mul…