What Matters in Practical Learned Image Compression

• URL: http://arxiv.org/abs/2605.05148v1
• Date: Wed, 06 May 2026 17:17:51 GMT
• Title: What Matters in Practical Learned Image Compression
• Abstract summary: We conduct a study of the key modeling choices that govern the design of a practical learned image.<n>We then perform performance-aware neural architecture search over millions of backbone configurations.<n>We construct a new tradeoff between speed and perceptual quality.
• Score: 3.6892365510577037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet practical image codec is yet to be proposed. In this work, we aim to close this gap. We conduct a comprehensive study of the key modeling choices that govern the design of a practical learned image codec, jointly optimized for perceptual quality and runtime -- including within the ablations several novel techniques. We then perform performance-aware neural architecture search over millions of backbone configurations to identify models that achieve the target on-device runtime while maximizing compression performance as captured by perceptual metrics. We combine the various optimizations to construct a new codec that achieves a significantly improved tradeoff between speed and perceptual quality. Based on rigorous subjective user studies, it provides 2.3-3x bitrate savings against AV1, AV2, VVC, ECM and JPEG-AI, and 20-40% bitrate savings against the best learned codec alternatives. At the same time, on an iPhone 17 Pro Max, it encodes 12MP images as fast as 230ms, and decodes them in 150ms -- faster than most top ML-based codecs run on a V100 GPU.

Related papers

• PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding [74.2282307661978]
  Implicit neural representation (INR) has achieved remarkable progress in novel view synthesis and image/video coding in recent years.<n>In this work, we propose a feedforward INR image coding architecture, Practical INR Image Codec (PIC), that computes all the necessary information for INR network in a single forward pass.
  arXiv  Detail & Related papers  (2026-09-08T16:52:00Z)
• Accelerating Learned Video Compression via Low-Resolution Representation Learning [18.399027308582596]
  We introduce an efficiency-optimized framework for learned video compression that focuses on low-resolution representation learning. Our method achieves performance levels on par with the low-decay P configuration of the H.266 reference software VTM.
  arXiv  Detail & Related papers  (2024-07-23T12:02:57Z)
• Streaming-capable High-performance Architecture of Learned Image Compression Codecs [21.53261818914534]
  We present an alternative method to improving the runtime performance of various learned image compression models. Our architecture alone produces excellent performance without any change to the neural model itself. We show that our implementations excel in throughput and latency compared to the baseline.
  arXiv  Detail & Related papers  (2022-08-02T03:15:48Z)
• PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Framework [88.18310777246735]
  We propose an end-to-end image compression framework that achieves 200 MB/s for both compression and decompression with a single NVIDIA Tesla V100 GPU. Experiments show that our framework compresses better than PNG by a margin of 30% in multiple datasets.
  arXiv  Detail & Related papers  (2022-06-10T03:00:10Z)
• A Coding Framework and Benchmark towards Low-Bitrate Video Understanding [63.05385140193666]
  We propose a traditional-neural mixed coding framework that takes advantage of both traditional codecs and neural networks (NNs) The framework is optimized by ensuring that a transportation-efficient semantic representation of the video is preserved. We build a low-bitrate video understanding benchmark with three downstream tasks on eight datasets, demonstrating the notable superiority of our approach.
  arXiv  Detail & Related papers  (2022-02-06T16:29:15Z)
• A New Image Codec Paradigm for Human and Machine Uses [53.48873918537017]
  A new scalable image paradigm for both human and machine uses is proposed in this work. The high-level instance segmentation map and the low-level signal features are extracted with neural networks. An image is designed and trained to achieve the general-quality image reconstruction with the 16-bit gray-scale profile and signal features.
  arXiv  Detail & Related papers  (2021-12-19T06:17:38Z)
• Adaptation and Attention for Neural Video Coding [23.116987835862314]
  We propose an end-to-end learned video that introduces several architectural novelties as well as training novelties. As one architectural novelty, we propose to train the inter-frame model to adapt the motion estimation process based on the resolution of the input video. A second architectural novelty is a new neural block that combines concepts from split-attention based neural networks and from DenseNets.
  arXiv  Detail & Related papers  (2021-12-16T10:25:49Z)
• ELF-VC: Efficient Learned Flexible-Rate Video Coding [61.10102916737163]
  We propose several novel ideas for learned video compression which allow for improved performance for the low-latency mode. We benchmark our method, which we call ELF-VC, on popular video test sets UVG and MCL-JCV. Our approach runs at least 5x faster and has fewer parameters than all ML codecs which report these figures.
  arXiv  Detail & Related papers  (2021-04-29T17:50:35Z)
• Conditional Entropy Coding for Efficient Video Compression [82.35389813794372]
  We propose a very simple and efficient video compression framework that only focuses on modeling the conditional entropy between frames. We first show that a simple architecture modeling the entropy between the image latent codes is as competitive as other neural video compression works and video codecs. We then propose a novel internal learning extension on top of this architecture that brings an additional 10% savings without trading off decoding speed.
  arXiv  Detail & Related papers  (2020-08-20T20:01:59Z)
• Content Adaptive and Error Propagation Aware Deep Video Compression [110.31693187153084]
  We propose a content adaptive and error propagation aware video compression system. Our method employs a joint training strategy by considering the compression performance of multiple consecutive frames instead of a single frame. Instead of using the hand-crafted coding modes in the traditional compression systems, we design an online encoder updating scheme in our system.
  arXiv  Detail & Related papers  (2020-03-25T09:04:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.