Image Denoising with Control over Deep Network Hallucination
Deep image denoisers achieve state-of-the-art results but with a hidden cost. As witnessed in recent literature, these deep networks are capable of overfitting their training distributions, causing inaccurate hallucinations to be added to the output and generalizing poorly to varying data. For better control and interpretability over a deep denoiser, we propose a novel framework exploiting a denoising network. We call it controllable confidence-based image denoising (CCID). In this framework, we exploit the outputs of a deep denoising network alongside an image convolved with a reliable filter. Such a filter can be a simple convolution kernel which does not risk adding hallucinated information. We propose to fuse the two components with a frequency-domain approach that takes into account the reliability of the deep network outputs. With our framework, the user can control the fusion of the two components in the frequency domain. We also provide a user-friendly map estimating spatially the confidence in the output that potentially contains network hallucination. Results show that our CCID not only provides more interpretability and control, but can even outperform both the quantitative performance of the deep denoiser and that of the reliable filter, especially when the test data diverge from the training data.
Code (1)
Tasks
DenoisingHallucinationImage DenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Self-Controlled Diffusion for Denoising in Scientific Imaging
This paper presents a novel approach for denoising Electron Backscatter Diffraction (EBSD) patterns using diffusion models. We propose a two-stage training process with a UNet-based architecture, incorporating an auxilia…
DenoisingTraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
Diffusion large language models (D-LLMs) have recently emerged as a promising alternative to auto-regressive LLMs (AR-LLMs). However, the hallucination problem in D-LLMs remains underexplored, limiting their reliability …
Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models
While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely un…
Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration
Text-Aware Image Restoration (TAIR) aims to recover high-quality images from low-quality inputs containing degraded textual content. While diffusion models provide strong generative priors for general image restoration, …
Image RestorationText SpottingDynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning
Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models due to their iterative refinement capabilities. However, hallucinations remain a critical issue that hinders thei…