{"total":664,"rows":[{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301,"area":null},{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233,"area":null},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221,"area":null},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211,"area":null},{"id":"2103.15306","title":"Checkerboard Context Model for Efficient Learned Image Compression","created":"2021-03-29","cited_by_count":202,"area":null},{"id":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170,"area":"diffusion"},{"id":"2302.14402","title":"Neural Video Compression with Diverse Contexts","created":"2023-02-28","cited_by_count":165,"area":null},{"id":"2112.04267","title":"Implicit Neural Representations for Image Compression","created":"2021-12-08","cited_by_count":162,"area":null},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153,"area":null},{"id":"2203.08450","title":"The Devil Is in the Details: Window-based Attention for Image Compression","created":"2022-03-16","cited_by_count":147,"area":null},{"id":"2207.05894","title":"Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression","created":"2022-07-13","cited_by_count":128,"area":null},{"id":"2111.13850","title":"Temporal Context Mining for Learned Video Compression","created":"2021-11-27","cited_by_count":117,"area":null},{"id":"2202.05492","title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression","created":"2022-02-11","cited_by_count":107,"area":null},{"id":"2108.03690","title":"Enhanced Invertible Encoding for Learned Image Compression","created":"2021-08-08","cited_by_count":105,"area":null},{"id":"2310.10325","title":"Towards image compression with perfect realism at ultra-low bitrates","created":"2023-10-16","cited_by_count":103,"area":null},{"id":"2403.08551","title":"GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting","created":"2024-03-13","cited_by_count":99,"area":null},{"id":"2301.11189","title":"Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models","created":"2023-01-26","cited_by_count":94,"area":null},{"id":"2211.07273","title":"MLIC: Multi-Reference Entropy Model for Learned Image Compression","created":"2022-11-14","cited_by_count":84,"area":null},{"id":"2201.12904","title":"COIN++: Neural Compression Across Modalities","created":"2022-01-30","cited_by_count":82,"area":null},{"id":"2404.09458","title":"CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting","created":"2024-04-15","cited_by_count":82,"area":null},{"id":"2212.13824","title":"Multi-Realism Image Compression with a Conditional Generator","created":"2022-12-28","cited_by_count":80,"area":null},{"id":"2502.14831","title":"Improving the Diffusability of Autoencoders","created":"2025-02-20","cited_by_count":80,"area":"diffusion"},{"id":"2502.20762","title":"Towards Practical Real-Time Neural Video Compression","created":"2025-02-28","cited_by_count":80,"area":null},{"id":"2202.06533","title":"An Introduction to Neural Data Compression","created":"2022-02-14","cited_by_count":79,"area":null},{"id":"2112.10961","title":"Nonlinear Transform Source-Channel Coding for Semantic Communications","created":"2021-12-21","cited_by_count":76,"area":null},{"id":"2206.07307","title":"VCT: A Video Compression Transformer","created":"2022-06-15","cited_by_count":74,"area":null},{"id":"2111.10633","title":"Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression","created":"2021-11-20","cited_by_count":70,"area":null},{"id":"2111.06707","title":"Transformer-based Image Compression","created":"2021-11-12","cited_by_count":62,"area":null},{"id":"2105.02158","title":"VoxelContext-Net: An Octree based Framework for Point Cloud Compression","created":"2021-05-05","cited_by_count":61,"area":null},{"id":"2404.18820","title":"Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior","created":"2024-04-29","cited_by_count":60,"area":"diffusion"},{"id":"2108.09551","title":"Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform","created":"2021-08-21","cited_by_count":58,"area":null},{"id":"2307.15421","title":"MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression","created":"2023-07-28","cited_by_count":58,"area":null},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58,"area":null},{"id":"2206.07460","title":"Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction","created":"2022-06-15","cited_by_count":55,"area":null},{"id":"2312.02753","title":"C3: High-performance and low-complexity neural compression from a single image or video","created":"2023-12-05","cited_by_count":55,"area":null},{"id":"2112.04487","title":"Joint Global and Local Hierarchical Priors for Learned Image Compression","created":"2021-12-08","cited_by_count":54,"area":null},{"id":"2306.04744","title":"WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models","created":"2023-06-07","cited_by_count":53,"area":"diffusion"},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52,"area":null},{"id":"2104.05168","title":"Soft then Hard: Rethinking the Quantization in Neural Image Compression","created":"2021-04-12","cited_by_count":51,"area":null},{"id":"2212.14593","title":"NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling","created":"2022-12-30","cited_by_count":51,"area":null},{"id":"2205.13129","title":"Wireless Deep Video Semantic Transmission","created":"2022-05-26","cited_by_count":50,"area":null},{"id":"2302.05071","title":"EVC: Towards Real-Time Neural Image Compression with Mask Decay","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2108.09993","title":"Image coding for machines: an end-to-end learned approach","created":"2021-08-23","cited_by_count":47,"area":null},{"id":"2207.05315","title":"CANF-VC: Conditional Augmented Normalizing Flows for Video Compression","created":"2022-07-12","cited_by_count":46,"area":null},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46,"area":null},{"id":"2203.02452","title":"Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression","created":"2022-03-04","cited_by_count":45,"area":null},{"id":"2203.10897","title":"Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression","created":"2022-03-21","cited_by_count":43,"area":null},{"id":"2109.03082","title":"Perceptual Learned Video Compression with Recurrent Conditional GAN","created":"2021-09-07","cited_by_count":41,"area":null},{"id":"2302.14677","title":"Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger","created":"2023-02-28","cited_by_count":40,"area":null},{"id":"2103.15726","title":"Slimmable Compressive Autoencoders for Practical Neural Image Compression","created":"2021-03-29","cited_by_count":39,"area":null},{"id":"2101.08687","title":"Overfitting for Fun and Profit: Instance-Adaptive Data Compression","created":"2021-01-21","cited_by_count":38,"area":null},{"id":"2409.08481","title":"USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020s","created":"2024-09-13","cited_by_count":37,"area":null},{"id":"2107.12038","title":"Neural Video Compression using GANs for Detail Synthesis and Propagation","created":"2021-07-26","cited_by_count":36,"area":null},{"id":"2208.04094","title":"Towards Semantic Communications: Deep Learning-Based Image Semantic Coding","created":"2022-08-08","cited_by_count":36,"area":null},{"id":"2404.08580","title":"Lossy Image Compression with Foundation Diffusion Models","created":"2024-04-12","cited_by_count":36,"area":"diffusion"},{"id":"2107.06463","title":"Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules","created":"2021-07-14","cited_by_count":35,"area":null},{"id":"2208.13056","title":"Lossy Image Compression with Quantized Hierarchical VAEs","created":"2022-08-27","cited_by_count":35,"area":null},{"id":"2301.05489","title":"A Residual Diffusion Model for High Perceptual Quality Codec Augmentation","created":"2023-01-13","cited_by_count":35,"area":"diffusion"},{"id":"2412.01615","title":"OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking","created":"2024-12-02","cited_by_count":35,"area":null},{"id":"2212.07372","title":"Image Compression with Product Quantized Masked Image Modeling","created":"2022-12-14","cited_by_count":33,"area":null},{"id":"2506.21977","title":"StableCodec: Taming One-Step Diffusion for Extreme Image Compression","created":"2025-06-27","cited_by_count":33,"area":"diffusion"},{"id":"2302.08899","title":"QARV: Quantization-Aware ResNet VAE for Lossy Image Compression","created":"2023-02-16","cited_by_count":32,"area":null},{"id":"2409.17557","title":"Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designs","created":"2024-09-26","cited_by_count":32,"area":null},{"id":"2108.11898","title":"Supervised Compression for Resource-Constrained Edge Computing Systems","created":"2021-08-21","cited_by_count":31,"area":null},{"id":"2207.01932","title":"Image Coding for Machines with Omnipotent Feature Learning","created":"2022-07-05","cited_by_count":31,"area":null},{"id":"2211.07793","title":"Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models","created":"2022-11-14","cited_by_count":31,"area":"diffusion"},{"id":"2309.15848","title":"SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations","created":"2023-09-27","cited_by_count":31,"area":null},{"id":"2411.18473","title":"HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compression","created":"2024-11-27","cited_by_count":31,"area":null},{"id":"2104.00531","title":"Extending Neural P-frame Codecs for B-frame Coding","created":"2021-03-30","cited_by_count":30,"area":null},{"id":"2203.04963","title":"Neural Data-Dependent Transform for Learned Image Compression","created":"2022-03-09","cited_by_count":30,"area":null},{"id":"2402.16749","title":"MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model","created":"2024-02-26","cited_by_count":30,"area":null},{"id":"2504.00496","title":"Learned Image Compression with Dictionary-based Entropy Model","created":"2025-04-01","cited_by_count":30,"area":null},{"id":"2401.08920","title":"Idempotence and Perceptual Image Compression","created":"2024-01-17","cited_by_count":29,"area":null},{"id":"2409.07414","title":"NVRC: Neural Video Representation Compression","created":"2024-09-11","cited_by_count":29,"area":null},{"id":"2112.09529","title":"End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compression","created":"2021-12-17","cited_by_count":28,"area":null},{"id":"2207.14678","title":"AlphaVC: High-Performance and Efficient Learned Video Compression","created":"2022-07-29","cited_by_count":28,"area":null},{"id":"2405.15413","title":"MambaVC: Learned Visual Compression with Selective State Spaces","created":"2024-05-24","cited_by_count":28,"area":"ssm"},{"id":"2106.02782","title":"On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework","created":"2021-06-05","cited_by_count":27,"area":null},{"id":"2503.18421","title":"4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video","created":"2025-03-24","cited_by_count":27,"area":null},{"id":"2112.09300","title":"Towards End-to-End Image Compression and Analysis with Transformers","created":"2021-12-17","cited_by_count":26,"area":null},{"id":"2407.09853","title":"Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation","created":"2024-07-13","cited_by_count":26,"area":null},{"id":"2505.16687","title":"One-Step Diffusion-Based Image Compression with Semantic Distillation","created":"2025-05-22","cited_by_count":26,"area":"diffusion"},{"id":"2112.06334","title":"DPICT: Deep Progressive Image Compression Using Trit-Planes","created":"2021-12-12","cited_by_count":25,"area":null},{"id":"2112.08691","title":"Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning","created":"2021-12-16","cited_by_count":25,"area":null},{"id":"2305.19185","title":"Compression with Bayesian Implicit Neural Representations","created":"2023-05-30","cited_by_count":25,"area":null},{"id":"2501.09815","title":"Lossy Compression with Pretrained Diffusion Models","created":"2025-01-16","cited_by_count":25,"area":"diffusion"},{"id":"2102.02913","title":"Progressive Neural Image Compression with Nested Quantization and Latent Ordering","created":"2021-02-04","cited_by_count":24,"area":null},{"id":"2203.09208","title":"Neural Compression-Based Feature Learning for Video Restoration","created":"2022-03-17","cited_by_count":23,"area":null},{"id":"2304.06244","title":"Computationally-Efficient Neural Image Compression with Shallow Decoders","created":"2023-04-13","cited_by_count":23,"area":null},{"id":"2401.15864","title":"Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression","created":"2024-01-29","cited_by_count":23,"area":null},{"id":"2403.02944","title":"Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity","created":"2024-03-05","cited_by_count":23,"area":null},{"id":"2410.02640","title":"RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion","created":"2024-10-03","cited_by_count":23,"area":"diffusion"},{"id":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23,"area":null},{"id":"2512.20194","title":"Generative Latent Coding for Ultra-Low Bitrate Image Compression","created":"2025-12-23","cited_by_count":23,"area":null},{"id":"2209.04847","title":"Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression","created":"2022-09-11","cited_by_count":22,"area":null},{"id":"2301.09479","title":"Modality-Agnostic Variational Compression of Implicit Neural Representations","created":"2023-01-23","cited_by_count":22,"area":null},{"id":"2405.03376","title":"CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer","created":"2024-05-06","cited_by_count":22,"area":null},{"id":"2303.05715","title":"Context-Based Trit-Plane Coding for Progressive Image Compression","created":"2023-03-10","cited_by_count":21,"area":null}],"next_cursor":"100"}