Guetzli: Perceptually Guided JPEG Encoder

03/13/2017
by   Jyrki Alakuijala, et al.
0

Guetzli is a new JPEG encoder that aims to produce visually indistinguishable images at a lower bit-rate than other common JPEG encoders. It optimizes both the JPEG global quantization tables and the DCT coefficient values in each JPEG block using a closed-loop optimizer. Guetzli uses Butteraugli, our perceptual distance metric, as the source of feedback in its optimization process. We reach a 29-45 according to Butteraugli, in comparison to other compressors we tried. Guetzli's computation is currently extremely slow, which limits its applicability to compressing static content and serving as a proof- of-concept that we can achieve significant reductions in size by combining advanced psychovisual models with lossy compression techniques.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 7

research
03/10/2021

Quantization-Guided Training for Compact TinyML Models

We propose a Quantization Guided Training (QGT) method to guide DNN trai...
research
08/03/2020

The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study

Handling digital images is almost always accompanied by a lossy compress...
research
11/25/2020

Reduced Reference Perceptual Quality Model and Application to Rate Control for 3D Point Cloud Compression

In rate-distortion optimization, the encoder settings are determined by ...
research
10/06/2021

8-bit Optimizers via Block-wise Quantization

Stateful optimizers maintain gradient statistics over time, e.g., the ex...
research
03/03/2021

User Generated HDR Gaming Video Streaming: Dataset, Codec Comparison and Challenges

Gaming video streaming services have grown tremendously in the past few ...
research
09/04/2023

Memory Efficient Optimizers with 4-bit States

Optimizer states are a major source of memory consumption for training n...
research
06/24/2022

Insect-inspired Visually-guided Decentralized Swarming

This paper addresses the need for fast, lightweight, vision-guided swarm...

Please sign up or login with your details

Forgot password? Click here to reset