6 papers
FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility
Yihalem Yimolal Tiruneh, Muhammad Salman Ali, Uyoung Jeong +5
Reconstructing animatable 3D human avatars from monocular video is a fundamental problem in computer vision with broad applications in AR/VR and digital content creation. Existing…
SAGE: An Expert-Annotated South Asian GI Endoscopy Dataset for Multimodal Learning and Hallucination Analysis
Niyoj Oli, Sachin Acharya, Sandesh Pokhrel +7
Gastrointestinal cancers represent a growing health burden in the South Asian region, driven largely by rapid changes in socio-economic conditions and lifestyle habits. However, ea…
HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models
MD Khalequzzaman Chowdhury Sayem, Mubarrat Tajoar Chowdhury, Yihalem Yimolal Tiruneh +4
Understanding the fine-grained articulation of human hands is critical in high-stakes settings such as robot-assisted surgery, chip manufacturing, and AR/VR-based human-AI interact…
Estimating 2D Keypoints of Surgical Tools Using Vision-Language Models with Low-Rank Adaptation
Krit Duangprom, Tryphon Lambrou, Binod Bhattarai
This paper presents a novel pipeline for 2D keypoint estima- tion of surgical tools by leveraging Vision Language Models (VLMs) fine- tuned using a low rank adjusting (LoRA) techni…
Federated Foundation Model for GI Endoscopy Images
Alina Devkota, Annahita Amireskandari, Joel Palko +5
Gastrointestinal (GI) endoscopy is essential in identifying GI tract abnormalities in order to detect diseases in their early stages and improve patient outcomes. Although deep lea…
NCDD: Nearest Centroid Distance Deficit for Out-Of-Distribution Detection in Gastrointestinal Vision
Sandesh Pokhrel, Sanjay Bhandari, Sharib Ali +7
The integration of deep learning tools in gastrointestinal vision holds the potential for significant advancements in diagnosis, treatment, and overall patient care. A major challe…