[TCSVT 2025] A Survey on Text-Driven 360-Degree Panorama Generation

A unified inference and post-training framework for accelerated video generation.

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

C++ implementation of the ECCV 2016 paper, Natural Image Stitching with the Global Similarity Prior.

Dataset for image stitching by line-guided local warping with global similarity constraint, PR2018

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

SAM 3D Objects

Depth Anything 3

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

MotionStream: Real-Time Video Generation with Interactive Motion Controls

[ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

[SIGGRAPH Asia'25] Enabling Reference-based Camera Control via Context without Explicit 3D Estimation

[NeurIPS 2025] Pixel-Perfect Depth

Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional de…

[ICCV'25 Best Paper Candidate] Official Implementations for Paper: Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

[ICCV-2025] Official Pytorch implementation of "AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via a Deep Unfolding Paradigm"

[ICCV 2025] GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene

CoPart (ICCV 2025): A part-based 3D generation framework & the first large-scale part-level 3D dataset.

[SIGGRAPH Asia 2025] 4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Reference PyTorch implementation and models for DINOv3

Streamlining Cartoon Production with Generative Post-Keyframing

[ICCV 2025] This is the official PyTorch codes for the paper: "DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution"

A curated list of recent diffusion models for video generation, editing, and various other applications.

We achieves high-quality first-frame guided video editing given a reference image, while maintaining flexibility for incorporating additional reference conditions.

[CVPR 2025] Official Implementation of "PolarFree: Polarization-based Reflection-Free Imaging"

[CVPR 2025] Boosting Generative Novel View Synthesis with Sparse and Unposed Images

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers