Saved in:
Bibliographic Details
Main Authors: Zhang, Yunxiang, Li, Bingxuan, Kuznetsov, Alexandr, Jindal, Akshay, Diolatzis, Stavros, Chen, Kenneth, Sochenov, Anton, Kaplanyan, Anton, Sun, Qi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.01866
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913823327256576
author Zhang, Yunxiang
Li, Bingxuan
Kuznetsov, Alexandr
Jindal, Akshay
Diolatzis, Stavros
Chen, Kenneth
Sochenov, Anton
Kaplanyan, Anton
Sun, Qi
author_facet Zhang, Yunxiang
Li, Bingxuan
Kuznetsov, Alexandr
Jindal, Akshay
Diolatzis, Stavros
Chen, Kenneth
Sochenov, Anton
Kaplanyan, Anton
Sun, Qi
contents Neural image representations have emerged as a promising approach for encoding and rendering visual data. Combined with learning-based workflows, they demonstrate impressive trade-offs between visual fidelity and memory footprint. Existing methods in this domain, however, often rely on fixed data structures that suboptimally allocate memory or compute-intensive implicit models, hindering their practicality for real-time graphics applications. Inspired by recent advancements in radiance field rendering, we introduce Image-GS, a content-adaptive image representation based on 2D Gaussians. Leveraging a custom differentiable renderer, Image-GS reconstructs images by adaptively allocating and progressively optimizing a group of anisotropic, colored 2D Gaussians. It achieves a favorable balance between visual fidelity and memory efficiency across a variety of stylized images frequently seen in graphics workflows, especially for those showing non-uniformly distributed features and in low-bitrate regimes. Moreover, it supports hardware-friendly rapid random access for real-time usage, requiring only 0.3K MACs to decode a pixel. Through error-guided progressive optimization, Image-GS naturally constructs a smooth level-of-detail hierarchy. We demonstrate its versatility with several applications, including texture compression, semantics-aware compression, and joint image compression and restoration.
format Preprint
id arxiv_https___arxiv_org_abs_2407_01866
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Image-GS: Content-Adaptive Image Representation via 2D Gaussians
Zhang, Yunxiang
Li, Bingxuan
Kuznetsov, Alexandr
Jindal, Akshay
Diolatzis, Stavros
Chen, Kenneth
Sochenov, Anton
Kaplanyan, Anton
Sun, Qi
Computer Vision and Pattern Recognition
Graphics
Neural image representations have emerged as a promising approach for encoding and rendering visual data. Combined with learning-based workflows, they demonstrate impressive trade-offs between visual fidelity and memory footprint. Existing methods in this domain, however, often rely on fixed data structures that suboptimally allocate memory or compute-intensive implicit models, hindering their practicality for real-time graphics applications. Inspired by recent advancements in radiance field rendering, we introduce Image-GS, a content-adaptive image representation based on 2D Gaussians. Leveraging a custom differentiable renderer, Image-GS reconstructs images by adaptively allocating and progressively optimizing a group of anisotropic, colored 2D Gaussians. It achieves a favorable balance between visual fidelity and memory efficiency across a variety of stylized images frequently seen in graphics workflows, especially for those showing non-uniformly distributed features and in low-bitrate regimes. Moreover, it supports hardware-friendly rapid random access for real-time usage, requiring only 0.3K MACs to decode a pixel. Through error-guided progressive optimization, Image-GS naturally constructs a smooth level-of-detail hierarchy. We demonstrate its versatility with several applications, including texture compression, semantics-aware compression, and joint image compression and restoration.
title Image-GS: Content-Adaptive Image Representation via 2D Gaussians
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2407.01866