Image compression optimized for 3D reconstruction by utilizing deep neural networks

03/27/2020
by   Alex Golts, et al.
0

Computer vision tasks are often expected to be executed on compressed images. Classical image compression standards like JPEG 2000 are widely used. However, they do not account for the specific end-task at hand. Motivated by works on recurrent neural network (RNN)-based image compression and three-dimensional (3D) reconstruction, we propose unified network architectures to solve both tasks jointly. These joint models provide image compression tailored for the specific task of 3D reconstruction. Images compressed by our proposed models, yield 3D reconstruction performance superior as compared to using JPEG 2000 compression. Our models significantly extend the range of compression rates for which 3D reconstruction is possible. We also show that this can be done highly efficiently at almost no additional cost to obtain compression on top of the computation already required for performing the 3D reconstruction task.

READ FULL TEXT

page 5

page 9

page 10

page 12

research
03/16/2018

Towards Image Understanding from Deep Compression without Decoding

Motivated by recent work on deep neural network (DNN)-based image compre...
research
08/18/2016

Full Resolution Image Compression with Recurrent Neural Networks

This paper presents a set of full-resolution lossy image compression met...
research
09/04/2019

Faster and Accurate Classification for JPEG2000 Compressed Images in Networked Applications

JPEG2000 (j2k) is a highly popular format for image and video compressio...
research
03/06/2021

End-to-end optimized image compression for multiple machine tasks

An increasing share of captured images and videos are transmitted for st...
research
11/17/2020

Analyzing and Mitigating Compression Defects in Deep Learning

With the proliferation of deep learning methods, many computer vision pr...
research
05/13/2023

DNN-Compressed Domain Visual Recognition with Feature Adaptation

Learning-based image compression was shown to achieve a competitive perf...
research
04/16/2021

Learning-based Compression for Material and Texture Recognition

Learning-based image compression was shown to achieve a competitive perf...

Please sign up or login with your details

Forgot password? Click here to reset