7 papers
FDIM: A Feature-distance-based Generic Video Quality Metric for Versatile Codecs
Jiayi Wang, Lichun Zhang, Xiaoqi Zhuang +3
Video technology is advancing toward Ultra High Definition (UHD) and High Dynamic Range (HDR), which intensifies the need for higher compression efficiency for these high-specifica…
SigVLP: Sigmoid Volume-Language Pre-Training for Self-Supervised CT-Volume Adaptive Representation Learning
Jiayi Wang, Hadrien Reynaud, Ibrahim Ethem Hamamci +4
Large-scale, volumetric medical imaging datasets typically aggregate scans from different vendors and devices, resulting in highly variable resolution, slice thicknesses, and numbe…
Are Pose Estimators Ready for the Open World? STAGE: A GenAI Toolkit for Auditing 3D Human Pose Estimators
Nikita Kister, István Sárándi, Jiayi Wang +2
For safety-critical applications, it is crucial to audit 3D human pose estimators before deployment. Will the system break down if the weather or the clothing changes? Is it robust…
Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration
Che Liu, Yinda Chen, Haoyuan Shi +21
The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundati…
Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning
Jiayi Wang, Wei Dai, Haoyu Wang +3
In medical image segmentation, heterogeneous privacy policies across institutions often make joint training on pooled datasets infeasible, motivating continual image segmentation-l…
CTFlow: Video-Inspired Latent Flow Matching for 3D CT Synthesis
Jiayi Wang, Hadrien Reynaud, Franciskus Xaverius Erick +1
Generative modelling of entire CT volumes conditioned on clinical reports has the potential to accelerate research through data augmentation, privacy-preserving synthesis and reduc…