Awesome Feature Upsampling:

A collection of feature upsampling operators in computer vision. We mainly highlight operators published at top conferences and journals.

arXiv Preprint

• On Point Affiliation in Feature Upsampling [paper][code]
• A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling [paper]
• FeatSharp: Your Vision Model Features, Sharper [paper]

2024

• [ICLR] FEATUP: A MODEL-AGNOSTIC FRAMEWORK FOR FEATURES AT ANY RESOLUTION [paper][code]
• [ECCV] LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors [paper][code]
• [TPAMI] Frequency-aware Feature Fusion for Dense Image Prediction [paper][code]
• [IJCV] FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architectures [paper][code]
• [MM] LDA-AQU: Adaptive Query-guided Upsampling via Local Deformable Attention [paper][code]

2023

• [ICCV] Learning to Upsample by Learning to Sample [paper][code]
• [ICCV] The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior [paper][code]

2022

• [ECCV] FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling [paper][code]
• [NeurIPS] SAPA: Similarity-Aware Point Affiliation for Feature Upsampling [paper][code]
• [ECCV] Learning Implicit Feature Alignment Function for Semantic Segmentation [paper[code]

2021

• [TPAMI] CARAFE++: Unified Content-Aware ReAssembly of FEatures [paper][code]]
• [CVPR] Learning Affinity-Aware Upsampling for Deep Image Matting [paper][code]

2020

• [TPAMI] Index Networks[paper][code]

2019

• [CVPR] Pixel-Adaptive Convolutional Neural Networks [paper][code]
• [ICCV] CARAFE: Content-Aware ReAssembly of FEatures [paper][code]
• [ICCV] Indices Matter: Learning to Index for Deep Image Matting [paper][code]
• [CVPR] Fast End-to-End Trainable Guided Filter [paper][code]
• [CVPR] DUpsampling:Decoders Matter for Semantic Segmentation [paper]

2018

• [CVPR] Deep Image Prior [paper][code]

2017

• [TPAMI] SegNet: A deep convolutional encoder-decoder architecture for image segmentation [paper]

2016

• [CVPR] Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network [paper]
• [CVPR] Is the deconvolution layer the same as a convolutional layer? [paper]

2015

• [ICCV] Learning deconvolution network for semantic segmentation [paper]

Contributions:

Please feel free to send me pull requests or email to add links.