Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

2D keypoint detection with Pytorch Lightning and wandb

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Supplemental learning materials for "Fourier Feature Networks and Neural Volume Rendering"

Facebook360 Depth Estimation Pipeline - https://facebook.github.io/facebook360_dep

[CVPR23] FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

FastAPI framework, high performance, easy to learn, fast to code, ready for production

From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

SIGGRAPH Asia 2023: Code for "Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes"

Code for "CosyPose: Consistent multi-view multi-object 6D pose estimation", ECCV 2020.

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

Plenoxels: Radiance Fields without Neural Networks

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

[ECCV 2022] R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis

Let us control diffusion models!

Direct voxel grid optimization for fast radiance field reconstruction.

🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

[ECCV 2022] Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Official PyTorch Implementation of the CVPR23 Paper "DINER: Depth-aware Image-based NEural Radiance fields"

SIGGRAPH Asia 2022: Code for "Efficient Neural Radiance Fields for Interactive Free-viewpoint Video"

[AAAI 2025] DepthFM: Fast Monocular Depth Estimation with Flow Matching

Code release for DS-NeRF (Depth-supervised Neural Radiance Fields)

High-Resolution Image Synthesis with Latent Diffusion Models

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation