paper-with-me

홈 › Papers

DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision

2023-09-13 · Xiangchen Yin, Zhenda Yu, Xin Gao, Xiao Sun

Low-light image enhancement restores the colors and details of a single image and improves high-level visual tasks. However, restoring the lost details in the dark area is still a challenge relying only on the RGB domain. In this paper, we delve into frequency as a new clue into the model and propose a DCT-driven enhancement transformer (DEFormer) framework. First, we propose a learnable frequency branch (LFB) for frequency enhancement contains DCT processing and curvature-based frequency enhancement (CFE) to represent frequency features. Additionally, we propose a cross domain fusion (CDF) to reduce the differences between the RGB domain and the frequency domain. Our DEFormer has achieved superior results on the LOL and MIT-Adobe FiveK datasets, improving the dark detection performance.

📄 PDF Abstract BibTeX arXiv:2309.06941

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingImage EnhancementLow-Light Image Enhancement

Similar Papers 제목 키워드 기반

Deformable Mesh Transformer for 3D Human Mesh Recovery

2023-01-01 · CVPR 2023 1 · Yusuke Yoshiyasu

We present Deformable mesh transFormer (DeFormer), a novel vertex-based approach to monocular 3D human mesh recovery. DeFormer iteratively fits a body mesh model to an input image via a mesh alignment feedback loop f…

3D Hand Pose Estimation3D Human Pose EstimationDecoderHuman Mesh Recovery

DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image

2023-09-22 · ICCV 2023 1 · Di Liu, Xiang Yu, Meng Ye, Qilong Zhangli 외

Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics. By leveraging a set of primitives to represent the target shape, recent methods have achieved promising res…

Does Head Pose Correction Improve Biometric Facial Recognition?

2025-12-02 · Justin Norman, Hany Farid arxiv

Biometric facial recognition models often demonstrate significant decreases in accuracy when processing real-world images, often characterized by poor quality, non-frontal subject poses, and subject occlusions. We invest…

3D ReconstructionImage Restoration

GuideFormer: Transformers for Image Guided Depth Completion

2022-01-01 · CVPR 2022 1 · Kyeongha Rho, Jinsung Ha, Youngjung Kim

Depth completion has been widely studied to predict a dense depth image from its sparse measurement and a single color image. However, most state-of-the-art methods rely on static convolutional neural networks (CNNs)…

Depth Completion

DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering

2020-05-02 · ACL 2020 6 · Qingqing Cao, Harsh Trivedi, Aruna Balasubramanian, Niranjan Balasubramanian

Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It turns out that we can get by without inp…

Question Answering