Grounding Image Matching in 3D with MASt3R

Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text".

[ICCV2023] 🧊FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models

[ECCV 2022] Map-free Visual Relocalization: Metric Pose Relative to a Single Image

This repo accompanies the research paper, ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data and contains the data, scripts to visualize and proces…

Official Pytorch Implementation for "SceneScape: Text-Driven Consistent Scene Generation"

[CVPR2024] OmniSDF: OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees

Official code for arxiv paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”

DoGaussian: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

Is a geometric model required to synthesize novel views from a single image?

Code release for "Towards Better Generalization: Joint Depth-Pose Learning without PoseNet".

Official Code for MotionCtrl [SIGGRAPH 2024]

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

My implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"

[ECCV 2024] Fully Sparse 3D Occupancy Prediction & RayIoU Evaluation Metric

[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.

Code of "OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments".

[CVPR 2024] A world model for autonomous driving.

Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".