Official implementation of "EponaV2: Driving World Model with Comprehensive Future Reasoning"

[Arxiv'25] SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images

[CVPR 2026] LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging

[Arxiv'25] DINO-Tok: Adapting DINO for Visual Tokenizers

[MICCAI'25 Oral] Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video

Ultra-high definition benchmark for zero-shot image reconstruction evaluation, including 2293 images at 2k resolution sourced from the ground-truth test sets of HRSOD, LIU4k, UAVid, UHDM, and UHRSD…

Image and video Tokenizer/VAE selection guide, text and face reconstruction evaluation.

[TPAMI 2026] 3D and 4D World Modeling: A Survey

[IJRR'2026] DCReg: Decoupled Characterization for Efficient Degenerate LiDAR Registeration

[Arxiv'25] MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization

Official code for the paper: Depth Anything At Any Condition

Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)

All kind of experts that can collect data for e2e learning in CARLA; 根据现有的开源代码，收集的相关experts

CV-MOS:A Cross-View Model for Motion Segmentation

MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation

OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition

This repo is the offical PyTorch implementation of MF-MOS.

[RAL' 25 & IROS‘ 25] MapEval: Towards Unified, Robust and Efficient SLAM Map Evaluation Framework.

RaDe-GS: Rasterizing Depth in Gaussian Splatting

Beyond Pure Geometry: An Uncertainty-Driven Perspective on Long-Term LiDAR Localization

Code for "DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT"

[RA-L'24] BeautyMap: Binary-Encoded Adaptable Ground Matrix for Dynamic Points Removal in Global Maps

[ICCV 2025] Official Code for Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

[ICCV2023] NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

Large scale LiDAR-IMU dataset

Maximum/Minimum Eigenvalue/Eigenvector Decomposition from 4x4 Matrix

[MICCAI'24] Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction

This is the official repository of the ICRA2024 paper "Ada-Tracker: Soft Tissue Tracking via Inter-Frame and Adaptive-template Matching".