Datasets › Ultra-High Resolution Image Reconstruction Benchmark

Ultra-High Resolution Image Reconstruction Benchmark

Introduced by Mingkai Jia et al. in MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization14 Jul 2025 archive 2025-07-28

Ultra-high definition benchmark (UHDBench) includes 2293 images at 2k resolution sourced from the ground-truth test sets of HRSOD, LIU4k, UAVid, UHDM, and UHRSD. Images smaller than 2560 × 1440 are excluded.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Reconstruction Ultra-High Resolution Image Reconstruction Benchmark SD-VAE (16x16) rFID 1.07 High-Resolution Image Synthesis with Latent Diffusion Models compvis/stable-diffusion +40 6 Compare

Papers archive 2025-07-28

6 shown of 6 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 6. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization 1 1 14 Jul 2025 not harvested
Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation 2 1 6 Sep 2024 ran 3 of 3 samples (0 unverified; 1 pointer-only for licence)
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation 2 1 10 Jun 2024 ran 6 of 15 samples (9 unverified)
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction 3 1 3 Apr 2024 ran 5 of 11 samples (6 unverified)
High-Resolution Image Synthesis with Latent Diffusion Models 41 1 20 Dec 2021 ran 19 of 28 samples (9 unverified; 5 pointer-only for licence)
Taming Transformers for High-Resolution Image Synthesis 13 1 17 Dec 2020 ran 6 of 6 samples (0 unverified; 4 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY-SA 4.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • Ultra-High Resolution Image Reconstruction Benchmark

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections