5 papers
SinoSynth: A Physics-based Domain Randomization Approach for Generalizable CBCT Image Enhancement
Yunkui Pang, Yilin Liu, Xu Chen +2
Cone Beam Computed Tomography (CBCT) finds diverse applications in medicine. Ensuring high image quality in CBCT scans is essential for accurate diagnosis and treatment delivery. Y…
Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization
Yilin Liu, Yunkui Pang, Jiang Li +2
Untrained networks inspired by deep image priors have shown promising capabilities in recovering high-quality images from noisy or partial measurements without requiring training s…
The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior
Yilin Liu, Jiang Li, Yunkui Pang +2
Deep Image Prior (DIP) shows that some network architectures naturally bias towards smooth images and resist noises, a phenomenon known as spectral bias. Image denoising is an imme…
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization
Yunhao Ge, Zhi Xu, Yao Xiao +3
We focus on controllable disentangled representation learning (C-Dis-RL), where users can control the partition of the disentangled latent space to factorize dataset attributes (co…
Sketch-Inspector: a Deep Mixture Model for High-Quality Sketch Generation of Cats
Yunkui Pang, Zhiqing Pan, Ruiyang Sun +1
With the involvement of artificial intelligence (AI), sketches can be automatically generated under certain topics. Even though breakthroughs have been made in previous studies in…