Practical Exposure Correction: Great Truths Are Always Simple

• URL: http://arxiv.org/abs/2212.14245v1
• Date: Thu, 29 Dec 2022 09:52:13 GMT
• Title: Practical Exposure Correction: Great Truths Are Always Simple
• Authors: Long Ma, Tianjiao Ma, Xinwei Xue, Xin Fan, Zhongxuan Luo, Risheng Liu
• Abstract summary: We establish a Practical Exposure Corrector (PEC) that assembles the characteristics of efficiency and performance. We introduce an exposure adversarial function as the key engine to fully extract valuable information from the observation. Our experiments fully reveal the superiority of our proposed PEC.
• Score: 65.82019845544869
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Improving the visual quality of the given degraded observation by correcting exposure level is a fundamental task in the computer vision community. Existing works commonly lack adaptability towards unknown scenes because of the data-driven patterns (deep networks) and limited regularization (traditional optimization), and they usually need time-consuming inference. These two points heavily limit their practicability. In this paper, we establish a Practical Exposure Corrector (PEC) that assembles the characteristics of efficiency and performance. To be concrete, we rethink the exposure correction to provide a linear solution with exposure-sensitive compensation. Around generating the compensation, we introduce an exposure adversarial function as the key engine to fully extract valuable information from the observation. By applying the defined function, we construct a segmented shrinkage iterative scheme to generate the desired compensation. Its shrinkage nature supplies powerful support for algorithmic stability and robustness. Extensive experimental evaluations fully reveal the superiority of our proposed PEC. The code is available at https://rsliu.tech/PEC.

Related papers

• Exploring the Impact of Hand Pose and Shadow on Hand-washing Action Recognition [0.0]
  In this paper, we investigate how pose and shadow impact a classifier's performance. We show these are heavily impacted by pose and shadow conditions. It is intriguing to observe model accuracy drop to almost zero with bigger changes in pose.
  arXiv  Detail & Related papers  (2024-06-19T21:49:12Z)
• WSCLoc: Weakly-Supervised Sparse-View Camera Relocalization [42.85368902409545]
  WSCLoc is a system capable of being customized to various deep learning-based relocalization models. In the initial stage, WSCLoc employs a multilayer perceptron-based structure called WFT-NeRF to co-optimize image reconstruction quality. In the second stage, we co-optimize the pre-trained WFT-NeRF and WFT-Pose.
  arXiv  Detail & Related papers  (2024-03-22T15:15:44Z)
• What Matters When Repurposing Diffusion Models for General Dense Perception Tasks? [49.84679952948808]
  Recent works show promising results by simply fine-tuning T2I diffusion models for dense perception tasks. We conduct a thorough investigation into critical factors that affect transfer efficiency and performance when using diffusion priors. Our work culminates in the development of GenPercept, an effective deterministic one-step fine-tuning paradigm tailed for dense visual perception tasks.
  arXiv  Detail & Related papers  (2024-03-10T04:23:24Z)
• Robust Monocular Depth Estimation under Challenging Conditions [81.57697198031975]
  State-of-the-art monocular depth estimation approaches are highly unreliable under challenging illumination and weather conditions. We tackle these safety-critical issues with md4all: a simple and effective solution that works reliably under both adverse and ideal conditions.
  arXiv  Detail & Related papers  (2023-08-18T17:59:01Z)
• Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling [13.427887784558168]
  We introduce a novel adaptive vision system for efficient action recognition processing. Our system pre-scans the global context sampling scheme at low-resolution and decides to skip or request high-resolution features at salient regions for further processing. We validate the system on EPIC-KENS and UCF-101 datasets for action recognition, and show that our proposed approach can greatly speed up inference with a tolerable loss of accuracy compared with those from state-the-art baselines.
  arXiv  Detail & Related papers  (2022-07-12T01:18:58Z)
• Toward Fast, Flexible, and Robust Low-Light Image Enhancement [87.27326390675155]
  We develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage. We make comprehensive explorations to SCI's inherent properties including operation-insensitive adaptability and model-irrelevant generality.
  arXiv  Detail & Related papers  (2022-04-21T14:40:32Z)
• Illumination-Invariant Active Camera Relocalization for Fine-Grained Change Detection in the Wild [12.104718944788141]
  This paper studies an illumination-invariant active camera relocalization method, it improves both in relative pose estimation and scale estimation. We construct a linear system to obtain the absolute scale in each ACR by minimizing the image warping error. Our work greatly expands the feasibility of real-world fine-grained change monitoring tasks for cultural heritages.
  arXiv  Detail & Related papers  (2022-04-13T18:00:55Z)
• The Probabilistic Normal Epipolar Constraint for Frame-To-Frame Rotation Optimization under Uncertain Feature Positions [53.478856119297284]
  We introduce the probabilistic normal epipolar constraint (PNEC) that overcomes the limitation by accounting for anisotropic and inhomogeneous uncertainties in the feature positions. In experiments on synthetic data, we demonstrate that the novel PNEC yields more accurate rotation estimates than the original NEC. We integrate the proposed method into a state-of-the-art monocular rotation-only odometry system and achieve consistently improved results for the real-world KITTI dataset.
  arXiv  Detail & Related papers  (2022-04-05T14:47:11Z)
• Provably Efficient Causal Reinforcement Learning with Confounded Observational Data [135.64775986546505]
  We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting. We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
  arXiv  Detail & Related papers  (2020-06-22T14:49:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.