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.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Reference PyTorch implementation and models for DINOv3

The official code for PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction [IROS 2024 Oral]

The evaluation method of the accurate and efficient RGB-colorized reconstruction

[ICCV 2025 Highlight] DIMO: Diverse 3D Motion Generation for Arbitrary Objects

Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.

[ICLR2025] A PyTorch implementation for STORM: Spatiotemporal Reconstruction Model for Large-Scale Outdoor Scenes

(ICLR2025) Enhancing End-to-End Autonomous Driving with Latent World Model

[ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

[ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"

[AAAI 2026] OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model

This is the official implementation of UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

[IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

[CVPR 2025] UniScene: Unified Occupancy-centric Driving Scene Generation

[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

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

Offical code for PanopticRecon++ (PR++)

Official implementation of "DepthLab: From Partial to Complete"

[CVPR 2025] StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models

[CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

[ICCV 2025] Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

[ICCV'25]DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

🎞️ [NeurIPS'24] MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views

A comprehensive list of Implicit Representations and NeRF papers relating to Robotics/RL domain, including papers, codes, and related websites