8 papers
A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition
Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal +1
Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In suc…
Towards Robust Cross-Dataset Object Detection Generalization under Domain Specificity
Ritabrata Chakraborty, Hrishit Mitra, Shivakumara Palaiahnakote +1
Object detectors often perform well in-distribution, yet degrade sharply on a different benchmark. We study cross-dataset object detection (CD-OD) through a lens of setting specifi…
Degradation-Consistent Learning via Bidirectional Diffusion for Low-Light Image Enhancement
Jinhong He, Minglong Xue, Zhipu Liu +3
Low-light image enhancement aims to improve the visibility of degraded images to better align with human visual perception. While diffusion-based methods have shown promising perfo…
DFDNet: Dynamic Frequency-Guided De-Flare Network
Minglong Xue, Aoxiang Ning, Shivakumara Palaiahnakote +1
Strong light sources in nighttime photography frequently produce flares in images, significantly degrading visual quality and impacting the performance of downstream tasks. While s…
A Transformer Based Handwriting Recognition System Jointly Using Online and Offline Features
Ayush Lodh, Ritabrata Chakraborty, Shivakumara Palaiahnakote +1
We posit that handwriting recognition benefits from complementary cues carried by the rasterized complex glyph and the pen's trajectory, yet most systems exploit only one modality.…
UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior
Minglong Xue, Shuaibin Fan, Shivakumara Palaiahnakote +1
Image dehazing techniques aim to enhance contrast and restore details, which are essential for preserving visual information and improving image processing accuracy. Existing metho…