SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.01064 · CVPR · 2023

Real-time 6K Image Rescaling with Rate-distortion Optimization

Qifeng Chen, Xin Yang, Ying-Cong Chen, Chenyang Qi, Ka Leong Cheng

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
abnervictor/hyperthumbnail canonical 3 of 7
FunctionStatusWhere it lives
get_act_function Ran abnervictor/hyperthumbnail/src/ops/modules.py
code served (permissive licence) · get_code("9c15d12caa8e49d1")
get_norm_function Ran abnervictor/hyperthumbnail/src/ops/modules.py
code served (permissive licence) · get_code("a4c0a276281ee685")
noise_round Ran abnervictor/hyperthumbnail/src/ops/compression_modules.py
code served (permissive licence) · get_code("db467a9af41459ff")
AttentionBlock Not yet run abnervictor/hyperthumbnail/BasicSR/basicsr/archs/dfdnet_util.py
code served (permissive licence) · get_code("8d3cd21cd5c3181a")
adaptive_instance_normalization Not yet run abnervictor/hyperthumbnail/BasicSR/basicsr/archs/dfdnet_util.py
code served (permissive licence) · get_code("b7c6741eed724350")
calc_mean_std Not yet run abnervictor/hyperthumbnail/BasicSR/basicsr/archs/dfdnet_util.py
code served (permissive licence) · get_code("a7e8af4ef5efc131")
get_part_location Not yet run abnervictor/hyperthumbnail/BasicSR/inference/inference_dfdnet.py
code served (permissive licence) · get_code("9adf4d768799f874")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Contemporary image rescaling aims at embedding a high-resolution (HR) image into a low-resolution (LR) thumbnail image that contains embedded information for HR image reconstruction. Unlike traditional image superresolution, this enables high-fidelity HR image restoration faithful to the original one, given the embedded information in the LR thumbnail. However, state-of-the-art image rescaling methods do not optimize the LR image file size for efficient sharing and fall short of real-time performance for ultra-high-resolution (e.g., 6K) image reconstruction. To address these two challenges, we propose a novel framework (HyperThumbnail) for real-time 6K rate-distortionaware image rescaling. Our framework first embeds an HR image into a JPEG LR thumbnail by an encoder with our proposed quantization prediction module, which minimizes the file size of the embedding LR JPEG thumbnail while maximizing HR reconstruction quality. Then, an efficient frequency-aware decoder reconstructs a high-fidelity HR image from the LR one in real time. Extensive experiments demonstrate that our framework outperforms previous image rescaling baselines in rate-distortion performance and can perform 6K image reconstruction in real time.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2304.01064")
get_code_for_paper("2304.01064")
have("2304.01064")

Connect an agent — have() is free.