3 papers
cs.CV2026
F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling
Huanjing Yue, Dawei Li, Shaoxiong Tu +1
Reconstructing High Dynamic Range (HDR) videos from sequences of alternating-exposure Low Dynamic Range (LDR) frames remains highly challenging, especially under dynamic scenes whe…
cs.CV2026
SpiralDiff: Spiral Diffusion with LoRA for RGB-to-RAW Conversion Across Cameras
Huanjing Yue, Shangbin Xie, Cong Cao +4
RAW images preserve superior fidelity and rich scene information compared to RGB, making them essential for tasks in challenging imaging conditions. To alleviate the high cost of d…
cs.CV2026
OAHuman: Occlusion-Aware 3D Human Reconstruction from Monocular Images
Yuanwang Yang, Hongliang Liu, Muxin Zhang +4
Monocular 3D human reconstruction in real-world scenarios remains highly challenging due to frequent occlusions from surrounding objects, people, or image truncation. Such occlusio…