Code for MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency

Depth Anything 3

Official implementation and models for OVIE (One View Is Enough! Monocular Training for In-the-Wild Novel View Generation)

Official implementation of "From Blobs to Spokes: High-Fidelity Surface Reconstruction via Oriented Gaussians"

[CVPR 2026 (Oral)] MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping

Geometry-Grounded Gaussian Splatting

Official implementation for the paper "SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction."

[CVPR'24 Best Student Paper] Mip-Splatting: Alias-free 3D Gaussian Splatting

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

[SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Multi-Camera Hand-Eye Calibration Framework for calibrating a camera network with respect to a robot arm

(EarthVision 2025 - CVPR Workshop) Official repository of DAFA-LS, a dataset of satellite image time series for the task of archaeological looting detection.

RaDe-GS: Rasterizing Depth in Gaussian Splatting

CUDA accelerated rasterization of gaussian splatting

Official PyTorch implementation of the paper "Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs"

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

Code for "How far can we go with ImageNet for Text-to-Image generation?" paper

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Wan: Open and Advanced Large-Scale Video Generative Models

official implementation of the Polynomial Mixer

News: the 10k dataset is ready for download.

📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Let us control diffusion models!

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

PyTorch code and models for the DINOv2 self-supervised learning method.

Code for "Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation"