Alle Funktionen optimal nutzen: JETZT ANMELDEN

    Robust Image Denoising using Kernel Predicting Networks (Ohne Sprachangabe)

    In: Eurographics 2021 - Short Papers ; 37-40  ; 2021

    Wie erhalte ich diesen Titel?

    Zugriff prüfen
    Download
    Kommerziell Vergütung an den Verlag: 14,50 € Grundgebühr: 4,00 € Gesamtpreis: 18,50 €
    Akademisch Vergütung an den Verlag: 4,50 € Grundgebühr: 2,00 € Gesamtpreis: 6,50 €

    Exportieren, teilen und zitieren

    We present a new method for designing high quality denoisers that are robust to varying noise characteristics of input images. Instead of taking a conventional blind denoising approach or relying on explicit noise parameter estimation networks as well as invertible camera imaging pipeline models, we propose a two-stage model that first processes an input image with a small set of specialized denoisers, and then passes the resulting intermediate denoised images to a kernel predicting network that estimates per-pixel denoising kernels. We demonstrate that our approach achieves robustness to noise parameters at a level that exceeds comparable blind denoisers, while also coming close to state-of-the-art denoising quality for camera sensor noise.

    Inhaltsverzeichnis Konferenzband

    Die Inhaltsverzeichnisse werden automatisch erzeugt und basieren auf den im Index des TIB-Portals verfügbaren Einzelnachweisen der enthaltenen Beiträge. Die Anzeige der Inhaltsverzeichnisse kann daher unvollständig oder lückenhaft sein.

    1
    Ray Tracing Lossy Compressed Grid Primitives
    Benthin, Carsten / Vaidyanathan, Karthik / Woop, Sven et al. | 2021
    5
    Gaming in Elliptic Geometry
    Szirmay-Kalos, Laszlo / Magdics, Milán et al. | 2021
    9
    Modeling and Actuation of Cable-driven Silicone Soft Robots
    Frâncu, Mihail et al. | 2021
    13
    Interactive Synthesis of 3D Geometries of Blood Vessels
    Rauch, Nikolaus / Harders, Matthias et al. | 2021
    17
    Data-driven Garment Pattern Estimation from 3D Geometries
    Goto, Chihiro / Umetani, Nobuyuki et al. | 2021
    21
    Visualising the Transition of Large Networks via Dimensionality Reduction to Illustrate the Evolution of the Human Brain
    Ganglberger, Florian / Kaczanowska, Joanna / Haubensak, Wulf / Bühler, Katja et al. | 2021
    25
    Visualizing Errors in Rendered High Dynamic Range Images
    Andersson, Pontus / Nilsson, Jim / Shirley, Peter / Akenine-Möller, Tomas et al. | 2021
    29
    Automatic Hierarchical Arrangement of Vector Designs
    Fisher, Matthew / Agarwal, Vineet / Beri, Tarun et al. | 2021
    33
    Bregman Approach to Single Image De-Raining
    Szirmay-Kalos, Laszlo / Tóth, Márton et al. | 2021
    37
    Robust Image Denoising using Kernel Predicting Networks
    Cai, Zhilin / Zhang, Yang / Manzi, Marco / Oztireli, Cengiz / Gross, Markus / Aydin, Tunç Ozan et al. | 2021
    41
    SoftWalks: Real-Time, Two-Ways Interaction between a Character and Loose Grounds
    Paliard, Chloé / Alvarado, Eduardo / Rohmer, Damien / Cani, Marie-Paule et al. | 2021
    45
    Interactive Finite Element Model of Needle Insertion and Laceration
    Perrusi, Pedro Henrique Suruagy / Baksic, Paul / Courtecuisse, Hadrien et al. | 2021
    49
    Tight Normal Cone Merging for Efficient Collision Detection of Thin Deformable Objects
    Han, Dong-Hoon / Lee, Chang-Jin / Lee, Sangbin / Ko, Hyeong-Seok et al. | 2021
    53
    Interactive Simulation for easy Decision-making in Fluid Dynamics
    Wang, Mengchen / Férey, Nicolas / Magoulès, Frédéric / Bourdot, Patrick et al. | 2021
    57
    Auto-rigging 3D Bipedal Characters in Arbitrarily Poses
    Kim, Jeonghwan / Son, Hyeontae / Bae, Jinseok / Kim, Young Min et al. | 2021
    61
    Visual Analysis of Point Cloud Neighborhoods via Multi-Scale Geometric Measures
    Ritter, Marcel / Schiffner, Daniel / Harders, Matthias et al. | 2021

    Wie erhalte ich diesen Titel?

    Zugriff prüfen
    Download
    Kommerziell Vergütung an den Verlag: 14,50 € Grundgebühr: 4,00 € Gesamtpreis: 18,50 €
    Akademisch Vergütung an den Verlag: 4,50 € Grundgebühr: 2,00 € Gesamtpreis: 6,50 €

    Exportieren, teilen und zitieren

    Feedback