Search papers, labs, and topics across Lattice.
Affiliation:
5
5
7
CEM-TUDASR, a computationally efficient unsupervised Transformer-based super-resolution framework for WCE image enhancement without paired low-resolution (LR) and high-resolution (HR) training data, is proposed.
UnCapsTSR achieves up to 80% improvement in image quality for capsule endoscopy, transforming how we visualize gastrointestinal health.
SPARC-Net achieves up to 100% error reduction in shock-dominated PDEs by tackling the multi-causal failures of traditional PINNs head-on.
A unified benchmark reveals the trade-offs between pixel-wise accuracy and perceptual realism in state-of-the-art image super-resolution techniques.
PINNs get a boost: adaptive loss balancing and residual-based collocation cuts errors by up to 70% in stiff PDEs.
