paper-with-me

Papers

Deep Nonparametric Convexified Filtering for Computational Photography, Image Synthesis and Adversarial Defense

2023-09-13 · Jianqiao Wangni

We aim to provide a general framework of for computational photography that recovers the real scene from imperfect images, via the Deep Nonparametric Convexified Filtering (DNCF). It is consists of a nonparametric deep network to resemble the physical equations behind the image formation, such as denoising, super-resolution, inpainting, and flash. DNCF has no parameterization dependent on training data, therefore has a strong generalization and robustness to adversarial image manipulation. During inference, we also encourage the network parameters to be nonnegative and create a bi-convex function on the input and parameters, and this adapts to second-order optimization algorithms with insufficient running time, having 10X acceleration over Deep Image Prior. With these tools, we empirically verify its capability to defend image classification deep networks against adversary attack algorithms in real-time.

📄 PDF Abstract BibTeX arXiv:2309.06724

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial DefenseDenoisingimage-classificationImage ClassificationImage GenerationImage ManipulationSuper-Resolution

Similar Papers 제목 키워드 기반

BLADE: Filter Learning for General Purpose Computational Photography

2017-11-29 · Pascal Getreuer, Ignacio Garcia-Dorado, John Isidoro, Sungjoon Choi 외

The Rapid and Accurate Image Super Resolution (RAISR) method of Romano, Isidoro, and Milanfar is a computationally efficient image upscaling method using a trained set of filters. We describe a generalization of RAISR, w…

DemosaickingDenoisingImage Super-ResolutionSuper-Resolution

Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering

2015-11-16 · CVPR 2016 6 · Mohammad Najafi, Sarah Taghavi Namin, Mathieu Salzmann, Lars Petersson

Scene parsing has attracted a lot of attention in computer vision. While parametric models have proven effective for this task, they cannot easily incorporate new training data. By contrast, nonparametric approaches, whi…

Scene ParsingSuperpixels

A Simple Yet Effective Improvement to the Bilateral Filter for Image Denoising

2015-05-25 · Kollipara Rithwik, Kunal Narayan Chaudhury

The bilateral filter has diverse applications in image processing, computer vision, and computational photography. In particular, this non-linear filter is quite effective in denoising images corrupted with additive Gaus…

DenoisingImage DenoisingSSIM

Robust Image Filtering Using Joint Static and Dynamic Guidance

2015-06-01 · CVPR 2015 6 · Bumsub Ham, Minsu Cho, Jean Ponce

Regularizing images under a guidance signal has been used in various tasks in computer vision and computational photography, particularly for noise reduction and joint upsampling. The aim is to transfer fine structures o…

DenoisingSuper-Resolution

Aesthetic Features for Personalized Photo Recommendation

2018-08-31 · Yu Qing Zhou, Ga Wu, Scott Sanner, Putra Manggala

Many photography websites such as Flickr, 500px, Unsplash, and Adobe Behance are used by amateur and professional photography enthusiasts. Unlike content-based image search, such users of photography websites are not jus…

Collaborative FilteringImage RetrievalStyle Transfer