5 papers
Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuning
Qianfeng Yang, Xiang Chen, Pengpeng Li +3
Rain degrades the visual quality of multi-view images, which are essential for 3D scene reconstruction, resulting in inaccurate and incomplete reconstruction results. Existing data…
SmokeBench: A Real-World Dataset for Surveillance Image Desmoking in Early-Stage Fire Scenes
Wenzhuo Jin, Qianfeng Yang, Xianhao Wu +3
Early-stage fire scenes (0-15 minutes after ignition) represent a crucial temporal window for emergency interventions. During this stage, the smoke produced by combustion significa…
Proposal Report for the 2nd SciCAP Competition 2024
Pengpeng Li, Tingmin Li, Jingyuan Wang +2
In this paper, we propose a method for document summarization using auxiliary information. This approach effectively summarizes descriptions related to specific images, tables, and…
Learning A Spiking Neural Network for Efficient Image Deraining
Tianyu Song, Guiyue Jin, Pengpeng Li +3
Recently, spiking neural networks (SNNs) have demonstrated substantial potential in computer vision tasks. In this paper, we present an Efficient Spiking Deraining Network, called…
Low-light Object Detection
Pengpeng Li, Haowei Gu, Yang Yang
In this competition we employed a model fusion approach to achieve object detection results close to those of real images. Our method is based on the CO-DETR model, which was train…