Computer Graphics Forum, EarlyView.Abstract Correlation‐based rendering techniques continue to advance, and efficiently exploiting correlations between pixel estimates has become increasingly important. The deep combiner framework [BHHM20] allows us to fuse independent and correlated pixel estimates but focuses solely on spatial correlations.
W. Zhou, E. Hughes, T. Hachisuka
wiley +1 more source
Bayesian selective scan for robust long-horizon action recognition via reliability-aware discretization. [PDF]
Front Robot AIWang C.
europepmc +1 more source
Edge‐preserving noise for diffusion models
Computer Graphics Forum, EarlyView.Abstract Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information important for high‐quality generation. We introduce an edge‐preserving diffusion process that generalizes isotropic models via a hybrid noise scheme with an edge‐aware scheduler that smoothly transitions ...
Jente Vandersanden +3 more
wiley +1 more source
Automated CT Pulmonary Angiography-Derived Periclot Radiomics for CTEPH Detection. [PDF]
Pulm CircNardelli P +5 more
europepmc +1 more source
NAADF: Globally Illuminated Voxel Worlds Accelerated with Nested Axis‐Aligned Distance Fields
Computer Graphics Forum, EarlyView.Abstract Achieving realistic rendering of 3D scenes in real time using path tracing is challenging due to the high sample count required, with ray tracing as the bottleneck. Focusing on voxels as a geometry representation offers significant opportunities for optimizations, especially for tracing the rays, but also for computing the samples.
A. Ulschmid +4 more
wiley +1 more source
Lightweight Asymmetric Convolutional Residual Network for Efficient Motion Image Deblurring. [PDF]
Entropy (Basel)Li H, Yue Y, Li J, Guo Z, Wu M.
europepmc +1 more source
Visualizing Image Segmentation Network Behavior Through the Lens of Scale Space Analysis
Computer Graphics Forum, EarlyView.Abstract Deep neural networks are widely used for image segmentation, also in sensitive applications such as medical imaging or autonomous driving. However, few explainable AI methods are available that help developers understand such networks beyond classification.
A. C. Mikliss, T. Schultz
wiley +1 more source
Explicit Compression Degradation Estimations for Low-Sampling Single-Pixel Imaging using Hadamard Basis. [PDF]
Adv Sci (Weinh)Zhang H, Cao J, Zhou C, Yao H, Hao Q.
europepmc +1 more source
Circles of Confidence for Multi‐Label Geometry Completion
Computer Graphics Forum, EarlyView.Abstract Inside–outside classification is widely used for geometry processing tasks such as surface reconstruction, geometry completion, and calculating signed distance fields. We introduce a new integral formulation of this problem, which assigns confidence scores that points are inside or outside, given incomplete boundary geometry.
Z. Wei +4 more
wiley +1 more source
GS-MSDR: Gaussian Splatting with Multi-Scale Deblurring and Resolution Enhancement. [PDF]
Sensors (Basel)Wan F +5 more
europepmc +1 more source