6 papers · 1 filter
Data Augmentation Through Random Style Replacement
Qikai Yang, Cheng Ji, Huaiying Luo +2
In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with…
Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods
Yiming Zhou, Zixuan Zeng, Andi Chen +7
Exploring the capabilities of Neural Radiance Fields (NeRF) and Gaussian-based methods in the context of 3D scene reconstruction, this study contrasts these modern approaches with…
Regional Style and Color Transfer
Zhicheng Ding, Panfeng Li, Qikai Yang +2
This paper presents a novel contribution to the field of regional style transfer. Existing methods often suffer from the drawback of applying style homogeneously across the entire…
Confidence Trigger Detection: Accelerating Real-time Tracking-by-detection Systems
Zhicheng Ding, Zhixin Lai, Siyang Li +3
Real-time object tracking necessitates a delicate balance between speed and accuracy, a challenge exacerbated by the computational demands of deep learning methods. In this paper,…
Enhance Image-to-Image Generation with LLaVA-generated Prompts
Zhicheng Ding, Panfeng Li, Qikai Yang +1
This paper presents a novel approach to enhance image-to-image generation by leveraging the multimodal capabilities of the Large Language and Vision Assistant (LLaVA). We propose a…
Exploring Diverse Methods in Visual Question Answering
Panfeng Li, Qikai Yang, Xieming Geng +3
This study explores innovative methods for improving Visual Question Answering (VQA) using Generative Adversarial Networks (GANs), autoencoders, and attention mechanisms. Leveragin…