Welcome to the L2M repository! This is the official implementation of our ICCV'25 paper titled "Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space". To enable training from single ...

Abstract: With advances in CLIP-based models for long-text processing, the insufficient ability to capture visual details has emerged as a key bottleneck for fine-grained image–text matching. Our ...

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...

This is a project dedicated to restoring/recreating test card images historically used by the BBC, as close to the originals as possible - so that they are both authentic and suitable for generation ...

Abstract: In unsupervised medical image registration, encoder-decoder architectures are widely used to predict dense, full-resolution displacement fields from paired images. Despite their popularity, ...