Official repo for S3OD: Towards Generalizable Salient Object Detection with Synthetic Data

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

ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The official PyTorch implementation for the paper "Image-adaptive 3D Lookup Tables for Real-time Image Enhancement with Bilateral Grids" (accepted by ECCV 2024)

The official PyTorch implementation for the paper "Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables" (accepted by ICCV 2025)

[ECCV 2022 & T-PAMI 2024] Multiple Look-Up Tables for Efficient Image Restoration

[NeurIPS 2025] DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"

[TPAMI 2025 / NeurIPS 2023] Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping

Code for QuantVGGT: Quantized Visual Geometry Grounded Transformer

The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"

NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics

A Pytorch Implementation of Finite Scalar Quantization

[CVPR2025] Official PyTorch implementation of "EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation."

Motion-Aware Generative Frame Interpolation

Unreal Real-Time Super Resolution (URTSR) is a neural rendering method for highly efficient real-time rendering super resolution.

Source code for ICCV 2025 paper "FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases"

Honor of Kings AI Open Environment of Tencent

[CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

Muon is an optimizer for hidden layers in neural networks

[ICCV'23] VQD-SR: Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution

[CVPR 2024] Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Neural Graphics Model Gym is a Python® toolkit for developing real-time Neural Graphics machine learning models.

Examples showing how to use the Neural Graphics Model Gym

A Novel Approach to Video Super-Resolution using Frame Recurrence and Generative Adversarial Networks | Python3 | PyTorch | OpenCV2 | GANs | CNNs

Offical repo for "OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution"

Implementation of the SIGGRAPH Asia 2024 conference paper "A Statistical Approach to Monte Carlo Denoising" [Sakai et al. 2024] based on pbrt-v3