Papers with Code 아카이브
Image Compression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 11
- 보존된 평가 기록
- 22
Image Compression is an application of data compression for digital images to lower their storage and/or transmission requirements.
Source: Variable Rate Deep Image Compression With a Conditional Autoencoder
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Tencent/TFace
공식 코드Privacy-Preserving Face Recognition Using Trainable Feature Subtraction
https://github.com/VincentChandelier/SADN
공식 코드SADN: Learned Light Field Image Compression with Spatial-Angular Decorrelation
https://github.com/YannDubs/lossyless
공식 코드https://github.com/YannickStruempler/LearnedJPEG
공식 코드Learning to Improve Image Compression without Changing the Standard Decoder
https://github.com/YujunHuang063/3D-GP-LMVIC
공식 코드3D-LMVIC: Learning-based Multi-View Image Coding with 3D Gaussian Geometric Priors
https://github.com/ZJLiang6412/SynonymousImageCompression
공식 코드Synonymous Variational Inference for Perceptual Image Compression
https://github.com/ZhengxueCheng/Learned-Image-Compression-with-GMM-and-Attention
공식 코드Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
https://github.com/adgaudio/heartspot
공식 코드HeartSpot: Privatized and Explainable Data Compression for Cardiomegaly Detection
https://github.com/adnan-hossain/var-feat-comp
공식 코드Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
https://github.com/adnan-hossain/var_feat_comp
공식 코드Flexible Variable-Rate Image Feature Compression for Edge-Cloud Systems
https://github.com/adnortje/binet
공식 코드BINet: a binary inpainting network for deep patch-based image compression
https://github.com/aimerykong/predictive-filter-flow
공식 코드https://github.com/aiolus-x/norm-inr
공식 코드Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks
https://github.com/ajayjain/lmconv
공식 코드https://github.com/alimd94/DiQP
공식 코드https://github.com/amink8/folk
공식 코드Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning
https://github.com/angchen-dev/locjnd
공식 코드Localization of Just Noticeable Difference for Image Compression
https://github.com/appletea233/llava-st
공식 코드LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
https://github.com/aurorazengfh/mambaic
공식 코드MambaIC: State Space Models for High-Performance Learned Image Compression
https://github.com/ayziksha/DSIN
공식 코드https://github.com/baoyu2020/shiftlic
공식 코드ShiftLIC: Lightweight Learned Image Compression with Spatial-Channel Shift Operations
https://github.com/beiluo97/hflic
공식 코드HFLIC: Human Friendly Perceptual Learned Image Compression with Reinforced Transform
https://github.com/bits-back/bits-back
공식 코드Practical Lossless Compression with Latent Variables using Bits Back Coding
https://github.com/bosszhe/emiff
공식 코드https://github.com/bosszhe/vimi
공식 코드VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection
https://github.com/bowenl0218/bpgan-signal-compression
공식 코드Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization
https://github.com/buggyyang/cdc_compression
공식 코드https://github.com/bychao100/deep-lossy-plus-residual-coding
공식 코드Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression
https://github.com/bychao100/towards-image-compression-and-analysis-with-transformers
공식 코드Towards End-to-End Image Compression and Analysis with Transformers
https://github.com/bytedance/qraf
공식 코드QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression
https://github.com/caishilv/joint-ic-ll
공식 코드https://github.com/caoscott/SReC
공식 코드https://github.com/ceciliasalvatore/sfcca
공식 코드Supervised Feature Compression based on Counterfactual Analysis
https://github.com/chaoliatriken/tngps
공식 코드https://github.com/chengqingli/dct_sbr
공식 코드Recovering Sign Bits of DCT Coefficients in Digital Images as an Optimization Problem
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.