paper-with-me

홈 › Papers

Deep Random Projector: Accelerated Deep Image Prior

2023-01-01 · CVPR 2023 1 · Taihui Li, Hengkang Wang, Zhong Zhuang, Ju Sun

Deep image prior (DIP) has shown great promise in tackling a variety of image restoration (IR) and general visual inverse problems, needing no training data. However, the resulting optimization process is often very slow, inevitably hindering DIP's practical usage for time-sensitive scenarios. In this paper, we focus on IR, and propose two crucial modifications to DIP that help achieve substantial speedup: 1) optimizing the DIP seed while freezing randomly-initialized network weights, and 2) reducing the network depth. In addition, we reintroduce explicit priors, such as sparse gradient prior---encoded by total-variation regularization, to preserve the DIP peak performance. We evaluate the proposed method on three IR tasks, including image denoising, image super-resolution, and image inpainting, against the original DIP and variants, as well as the competing metaDIP that uses meta-learning to learn good initializers with extra data. Our method is a clear winner in obtaining competitive restoration quality in a minimal amount of time. Our code is available at https://github.com/sun-umn/Deep-Random-Projector.

📄 PDF Abstract BibTeX

Code (1)

sun-umn/deep-random-projector 공식 구현 pytorch

Tasks

DenoisingImage DenoisingImage InpaintingImage RestorationImage Super-ResolutionMeta-LearningSuper-Resolution

Similar Papers 제목 키워드 기반

GAN-based Projector for Faster Recovery with Convergence Guarantees in Linear Inverse Problems

2019-02-26 · ICCV 2019 10 · Ankit Raj, Yuqi Li, Yoram Bresler

A Generative Adversarial Network (GAN) with generator $G$ trained to model the prior of images has been shown to perform better than sparsity-based regularizers in ill-posed inverse problems. Here, we propose a new metho…

compressed sensingGenerative Adversarial NetworkSuper-Resolution

Ghost Projection

2021-09-03 · David Ceddia, David M. Paganin

Ghost imaging is a developing imaging technique that employs random masks to image a sample. Ghost projection utilizes ghost-imaging concepts to perform the complementary procedure of projection of a desired image. The k…

PKI: Prior Knowledge-Infused Neural Network for Few-Shot Class-Incremental Learning

2026-01-13 · Kexin Baoa, Fanzhao Lin, Zichen Wang, Yong Li 외 arxiv

Few-shot class-incremental learning (FSCIL) aims to continually adapt a model on a limited number of new-class examples, facing two well-known challenges: catastrophic forgetting and overfitting to new classes. Existing …

Few-Shot Class-Incremental Learning

A Projector-Based Approach to Quantifying Total and Excess Uncertainties for Sketched Linear Regression

2018-08-17 · Jocelyn T. Chi, Ilse C. F. Ipsen

Linear regression is a classic method of data analysis. In recent years, sketching -- a method of dimension reduction using random sampling, random projections, or both -- has gained popularity as an effective computatio…

Dimensionality Reductionregression

End-to-end Full Projector Compensation

2020-07-30 · Bingyao Huang, Tao Sun, Haibin Ling

Full projector compensation aims to modify a projector input image to compensate for both geometric and photometric disturbance of the projection surface. Traditional methods usually solve the two parts separately and ma…