20 results for βimage recoveryβ
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.β
Want pure semantic search? Try claim verification β
This paper proposes a method to improve the recovery of unobservable image structures in ill-posed imaging inverse problems using consecutive posterior fusion.
Ziwei Li, Wengu Chen, Huanmin Ge, Limei Huo +1 more
This paper introduces a new power-scale variation (PSV) with tunable parameters for image reconstruction and proposes an iteratively re-weighted least squares algorithm to solve the minimization problβ¦
Shen Zhou, Jinghui Zhang, Wenbo Huang, Xuwei Qian +6 more
QuReC is a unified framework for all-in-one image restoration using a Degradation-Guided Query Reconstruction Module and a Local-Global Response Calibration Module.
This paper constructs a graph-based image restoration system using unrolled networks and shows that the learned steps select an element of a Krylov subspace, constraining the hypothesis space.
This paper presents a two-stage recovery approach for camera-only low-cost unmanned ground vehicles to restore guideline tracking when lines are lost.
The paper introduces STARFISH, a novel healing method that efficiently recovers significant accuracy in heavily pruned neural networks by optimizing the pruned model to match the original network's inβ¦
A new method for image dehazing called FreePath that uses a neural mean free path framework to recover scene radiance.
This paper investigates the Plug and Play method for linear ill-posed problems using specialized MMSE estimators and derives recovery guarantees.
This paper analyzes the proprietary file system of Honeywell video surveillance devices, demonstrating that video data can be successfully recovered even after deletion using three different methods:β¦
This paper proposes using color statistics, specifically through novel color transformations, to detect AI-generated synthetic images by exploiting the color-imitation weaknesses of current generativeβ¦
This paper improves the foundations of neural likelihood approximation for Bayesian inverse problems by making the learning problem strictly convex and showing convergence to the true likelihood.
The paper introduces a method using a U-Net CNN to acquire and estimate detailed sub-surface scattering properties by learning the pixel footprint response, enabling high-resolution relighting of objeβ¦