Denoising Transformer

Denoising Transformers are a class of deep learning models designed to remove noise from various data types, including images and motion capture sequences, improving the accuracy and reliability of downstream tasks. Current research focuses on developing novel transformer architectures and algorithms, such as conditional denoising transformers and context-aware transformers, to enhance denoising performance, particularly in challenging scenarios like severe occlusions or non-uniform noise distributions. These advancements are significant because effective denoising is crucial for improving the robustness and accuracy of computer vision systems, particularly in applications like autonomous driving, robotics, and medical imaging, where noisy data is common. The development of efficient and effective denoising transformers is thus driving progress across numerous fields.

Papers

October 28, 2024

On Inductive Biases That Enable Generalization of Diffusion Transformers
Jie An, De Wang, Pengsheng Guo, Jiebo Luo, Alexander Schwing
Strong Generalization Inductive Bias Diffusion Transformer Denoising Transformer

September 10, 2024

Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening
Michael Adewole, Oluwaseyi Giwa, Favour Nerrise, Martins Osifeko, Ajibola Oyedeji
Human Motion Diffusion Based Human Motion Generation Stable Pose Motion Sequence Human Motion Synthesis Motion in Betweening Denoising Transformer

July 12, 2024

Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer
Yuanfei Huang, Hua Huang
Industrial Disturbing Noise Image Prior Learning Based Denoising Noise Prior Denoising Transformer

January 5, 2024

Denoising Vision Transformers
Jiawei Yang, Katie Z Luo, Jiefeng Li, Kilian Q Weinberger, Yonglong Tian, Yue Wang
Vision Transformer Learning Based Denoising Denoising Transformer

September 9, 2023

DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions
Teng Fu, Xiaocong Wang, Haiyang Yu, Ke Niu, Bin Li, Xiangyang Xue
Multi Object Tracking Motion Estimation Multiple Object Tracking Traditional Convolutional Multiple Object Denoising Transformer Mask Strategy Occlusion Aware Risk Assessment

September 7, 2023

Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy
Yi Tang, Takafumi Iwaguchi, Hiroshi Kawasaki
Image Enhancement Underwater Image Underwater Image Enhancement Non Uniform Transformer Based Diffusion Model Skip and Recover Denoising Transformer

April 4, 2023

Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer
Dan Zhang, Fangfang Zhou
Context Aware Real World Image Real World Image Denoising Context Aware Transformer Self Supervised Image Denoising Denoising Transformer

February 3, 2023

Offloading Deep Learning Powered Vision Tasks from UAV to 5G Edge Server with Denoising
Sedat Ozer, Enes Ilhan, Mehmet Akif Ozkanoglu, Hakan Ali Cirpan
Deep Learning Deep Network Denoising Process Noisy Image Edge Server Denoising Algorithm Denoising Transformer

Denoising Transformer

Papers

On Inductive Biases That Enable Generalization of Diffusion Transformers

Human Motion Synthesis_ A Diffusion Approach for Motion Stitching and In-Betweening

Beyond Image Prior: Embedding Noise Prior into Conditional Denoising Transformer

Denoising Vision Transformers

DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions

Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy

Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer

Offloading Deep Learning Powered Vision Tasks from UAV to 5G Edge Server with Denoising