Presentation

<
DPF: Differentiable Polyphase Filtering for Large-Kernel Approximation
SessionReal-Time Rendering
DescriptionWe introduce a novel Polyphase Filtering framework offering the fastest approximation for real-time, large-kernel image and video processing. Overcoming fixed-resolution processing constraints, our method efficiently handles complex, spatially-variant kernels. It significantly outperforms existing techniques, delivering unmatched computational speed and superior visual quality for dynamic post-processing and advanced visual effects.
Authors
Zhe Cao
State Key Lab of CAD and CG, Zhejiang University
Zhizhen Wu
State Key Lab of CAD and CG, Zhejiang University
Yuchi Huo
State Key Lab of CAD and CG, Zhejiang University
Zhonggui Chen
School of Informatics, Xiamen University
Rui Wang
State Key Lab of CAD and CG, Zhejiang University
Event Type
Technical Paper
TimeMonday, 20 July 20264:15pm - 4:25pm PDT
LocationRoom 408 A
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Monday, 20 July 20263:45pm - 5:15pm PDTRoom 408 A
Keywords
Rendering
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationGeneralized Spherical Harmonics Products using Spherical Grids
Similar Presentations
Real-Time GPU Vector Graphics SDF Generation Based on Quadratic Stroke Rendering
ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation
GauSmoke: Hybrid Physics-Optical Gaussian Splatting for Sparse Smoke Reconstruction