U-Net has become a cornerstone in various visual applications such as image segmentation
and diffusion probability models. While numerous innovative designs and improvements …

Recent advances in learning multi-modal representation have witnessed the success in
biomedical domains. While established techniques enable handling multi-modal …

The advent of 3D Gaussian Splatting (3D-GS) techniques and their dynamic scene modeling
variants, 4D-GS, offers promising prospects for real-time rendering of dynamic surgical …

Abstract 3D reconstruction of biological tissues from a collection of endoscopic images is a
key to unlock various important downstream surgical applications with 3D capabilities …

Recent advancements in large generative models and real-time neural rendering using
point-based techniques pave the way for a future of widespread visual data distribution …

Semi-supervised medical image segmentation aims to leverage limited annotated data and
rich unlabeled data to perform accurate segmentation. However, existing semi-supervised …

Open-vocabulary object detection (OVD) utilizes image-level cues to expand the linguistic
space of region proposals, thereby facilitating the detection of diverse novel classes. Recent …

Generative models hold promise for revolutionizing medical education, robot-assisted
surgery, and data augmentation for medical AI development. Diffusion models can now …

Diffusion-based video generation models have made significant strides, producing outputs
with improved visual fidelity, temporal coherence, and user control. These advancements …

Generating diverse plausible outputs from a single input is crucial for addressing visual
ambiguities, exemplified in medical imaging where experts may provide varying semantic …