Infinite Photorealistic Worlds using Procedural Generation

Pytorch implementation of DiffGlue for ACM MM'24 paper "DiffGlue: Diffusion-Aided Image Feature Matching", by Shihua Zhang and Jiayi Ma.

Video stabilization using gyroscope data

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

🔍 A Hex Editor for Reverse Engineers, Programmers and people who value their retinas when working at 3 AM.

This is the official Python and C++ implementation repository for a paper entitled "Track Initialization and Re-Identification for 3D Multi-View Multi-Object Tracking", Information Fusion (http://a…

Converts a position reference pass to a uv map that can be used to warp an image.

Fast and minimalist 3D viewer.

Mitsuba 3: A Retargetable Forward and Inverse Renderer

Marigold adapted for video estimation

All in one place

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Multi-Platform Package Manager for Stable Diffusion

The local version of the backend and UI for the gProfiler agent, featuring advanced flamegraph analysis tools. For the also free cloud version, please see https://profiler.granulate.io

Official Pytorch implementation of "Visual Style Prompting with Swapping Self-Attention"

Open-Sora: Democratizing Efficient Video Production for All

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

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Geospatial processing toolbox for environmental and climate studies

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration

Focus on prompting and generating

Custom processing nodes for AliceVision Meshroom to enhance GCP utilization capabilities

[CVPR 2024 Oral] Official repository of FMA-Net

A procedural Blender pipeline for photorealistic training image generation

Loading icons and small animations built with pure SVG.

Foundational Models for State-of-the-Art Speech and Text Translation