3 papers
cs.CV2025
Enabling Plant Phenotyping in Weedy Environments using Multi-Modal Imagery via Synthetic and Generated Training Data
Earl Ranario, Ismael Mayanja, Heesup Yun +2
Accurate plant segmentation in thermal imagery remains a significant challenge for high throughput field phenotyping, particularly in outdoor environments where low contrast betwee…
cs.CV2025
AGILE: A Diffusion-Based Attention-Guided Image and Label Translation for Efficient Cross-Domain Plant Trait Identification
Earl Ranario, Lars Lundqvist, Heesup Yun +2
Semantically consistent cross-domain image translation facilitates the generation of training data by transferring labels across different domains, making it particularly useful fo…
cs.CV2025
AgRowStitch: A High-fidelity Image Stitching Pipeline for Ground-based Agricultural Images
Isaac Kazuo Uyehara, Heesup Yun, Earl Ranario +1
Agricultural imaging often requires individual images to be stitched together into a final mosaic for analysis. However, agricultural images can be particularly challenging to stit…