Time-reversed scene reconstruction from thermal traces using Visual-Language Models and constrained diffusion.
An end-to-end framework that jointly learns task-specific hyperspectral band selection and a neural model for classification and segmentation.
Preprint: a gradient-regularized neural approach to compensate for modeled myopic defocus.
Preprint: a gradient-regularized neural approach to compensate for modeled myopic defocus.
Preprint: a multimodal benchmark and reconstruction framework for inferring recent human-environment interactions from residual physical traces.
Preprint: scene-driven adaptive ordering of Hadamard basis patterns for single-pixel spectral imaging.
Preprint: noise distribution agnostic self-supervised image denoising via learned recorruption.
Drone detection under high-illumination conditions remains a critical challenge due to sensor saturation, which degrades visual information and limits the performance of conventional detection models. A promising alternative to overcome this issue is …