paper-with-me

홈 › Papers

Multi-Realism Image Compression with a Conditional Generator

2022-12-28 · CVPR 2023 1 · Eirikur Agustsson, David Minnen, George Toderici, Fabian Mentzer

By optimizing the rate-distortion-realism trade-off, generative compression approaches produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions produced by rate-distortion optimized models. However, previous methods do not explicitly control how much detail is synthesized, which results in a common criticism of these methods: users might be worried that a misleading reconstruction far from the input image is generated. In this work, we alleviate these concerns by training a decoder that can bridge the two regimes and navigate the distortion-realism trade-off. From a single compressed representation, the receiver can decide to either reconstruct a low mean squared error reconstruction that is close to the input, a realistic reconstruction with high perceptual quality, or anything in between. With our method, we set a new state-of-the-art in distortion-realism, pushing the frontier of achievable distortion-realism pairs, i.e., our method achieves better distortions at high realism and better realism at low distortion than ever before.

📄 PDF Abstract BibTeX arXiv:2212.13824

Code (1)

Nikolai10/MRIC tf

Tasks

DecoderImage CompressionNavigate

Similar Papers 제목 키워드 기반

EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation

2023-09-06 · Nikolai Körber, Eduard Kromer, Andreas Siebert, Sascha Hauke 외

We introduce EGIC, an enhanced generative image compression method that allows traversing the distortion-perception curve efficiently from a single model. EGIC is based on two novel building blocks: i) OASIS-C, a conditi…

DecoderImage CompressionSemantic Segmentation

Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaption

2024-06-02 · Anqi Li, Feng Li, Yuxi Liu, Runmin Cong 외

Although recent generative image compression methods have demonstrated impressive potential in optimizing the rate-distortion-perception trade-off, they still face the critical challenge of flexible rate adaption to dive…

AllImage Compression

Towards Realistic Scene Generation with LiDAR Diffusion Models

2024-03-31 · CVPR 2024 1 · Haoxi Ran, Vitor Guizilini, Yue Wang

Diffusion models (DMs) excel in photo-realistic image synthesis, but their adaptation to LiDAR scene generation poses a substantial hurdle. This is primarily because DMs operating in the point space struggle to preserve …

3D geometryImage GenerationScene Generation

Conditional Perceptual Quality Preserving Image Compression

2023-08-16 · Tongda Xu, Qian Zhang, Yanghao Li, Dailan He 외

We propose conditional perceptual quality, an extension of the perceptual quality defined in \citet{blau2018perception}, by conditioning it on user defined information. Specifically, we extend the original perceptual qua…

Image Compression

Perception-based Image Denoising via Generative Compression

2026-02-12 · Nam Nguyen, Thinh Nguyen, Bella Bose arxiv

Image denoising aims to remove noise while preserving structural details and perceptual realism, yet distortion-driven methods often produce over-smoothed reconstructions, especially under strong noise and distribution s…

Image Denoising