🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

An open-source, web-based viewer for zoomable images, implemented in pure JavaScript.

Efficient vision foundation models for high-resolution generation and perception.

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

Let us democratise high-resolution generation! (CVPR 2024)

CogView4, CogView3-Plus and CogView3(ECCV 2024)

[CVPR 2024] An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

Official PyTorch implementation of Revisiting Image Pyramid Structure for High Resolution Salient Object Detection (ACCV 2022)

Official repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)

Hierarchical Image Pyramid Transformer - CVPR 2022 (Oral)

ComfyUI DyPE+SEGA, enabling artifact-free 4K+ image generation: Z-Image, Qwen, Flux, Krea2

[TVCG'2023] AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)

[TPAMI 2022] Learning Enriched Features for Fast Image Restoration and Enhancement. Results on Defocus Deblurring, Denoising, Super-resolution, and image enhancement

we'd like to think of this texture pack as a resource also, if you want to give sm64 your own look feel free to use these as a base for accuracy, just credit them render96 boys & girls

iipsrv is an advanced high-performance feature-rich image server for web-based streamed viewing and zooming of ultra high-resolution images.

[ECCV22] Official Implementation of HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation

Scaling Vision Pre-Training to 4K Resolution

FFHQR -- the first large-scale retouching dataset for computer vision research.