Stars
A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment…
⏰ AI conference deadline countdowns
👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...
Measures and metrics for image2image tasks. PyTorch.
PyTorch Lightning Optical Flow models, scripts, and pretrained weights.
[CVPR 2024] MemFlow: Optical Flow Estimation and Prediction with Memory
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)
Many-to-many Splatting for Efficient Video Frame Interpolation
DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)
Schedule-Free Optimization in PyTorch
[SIGGRAPH 2024] Mob-FGSR: Frame Generation and Super Resolution for Mobile Real-Time Rendering
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
IQA: Deep Image Structure and Texture Similarity Metric
an implementation of softmax splatting for differentiable forward warping using PyTorch
SportsSloMo: A New Benchmark and Baseline Models for Human-centric Video Frame Interpolation, CVPR 2024 (https://arxiv.org/abs/2308.16876)
Source code to pbrt, the ray tracer described in the forthcoming 4th edition of the "Physically Based Rendering: From Theory to Implementation" book.
High dynamic range (HDR) image viewer for graphics people
More practical frame interpolation approach.
WACV2024 - Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution
Perceptual video quality assessment based on multi-method fusion.
ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.
[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
[CVPR24] Official Implementation of GEM (Grounding Everything Module)
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform