Stars
An elegant PyTorch deep reinforcement learning library.
Optimization Based and Point Uncertainty Aware Radar-inertial Odometry for 4D Radar System
Simulation platform for general-purpose robotics & embodied AI learning.
[CVPR 2025] StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models
OpenVDB - Sparse volume data structure and tools
Doe-1: Closed-Loop Autonomous Driving with Large World Model
[CVPR 2025] Relative camera pose estimation and visual localization with Reloc3r
[ICLR'25] 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
[CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
[T-RO 2024] FALCON: Fast Autonomous Aerial Exploration using Coverage Path Guidance.
[CVPR 2025 Highlight] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
End-to-End SLAM with camera calibration, monocular prior integration and dense Rendering
[ICCV'25]DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion
H3-Mapping: Quasi-Heterogeneous Feature Grids for Real-time Dense Mapping Using Hierarchical Hybrid Representation (submitted to RAL 2024)
[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[RA-L] FM-Fusion: Instance-aware Semantic Mapping Boosted by Vision-Language Foundation Models
Implementation of LVSM, SOTA Large View Synthesis with Minimal 3d Inductive Bias, from Adobe Research
Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024
[ICCV 2025] VistaDream: Sampling multiview consistent images for single-view scene reconstruction
[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth
[TIP 2026] ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
Depth Any Video with Scalable Synthetic Data (ICLR 2025)