HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction

Curate, Annotate, and Manage Your Data in LightlyStudio.

Implemented BEVFormer support for BEV segmentation

Project page for Neural Shell Texture Splatting (ICCV 2025)

An end to end SQL agent, get the table using only natural language.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

XLeRobot: Practical Dual-Arm Mobile Home Robot for $660

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

Official implementation of BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting

[CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

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

3D高斯论文，持续更新，欢迎交流讨论。

[CVPR 2025] RelationField: Relate Anything in Radiance Fields

[NeurIPS 2024 Spotlight] Implementation of the paper "3D Gaussian Splatting as Markov Chain Monte Carlo"

[ICLR' 25] SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

Implementations of NeRF variants based on Taichi + PyTorch

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

This is an automatic full segmentation tool based on Segment-Anything-2 and Segment-Anything-1. Our tool performs automatic full segmentation of the video, enabling the tracking of each object and …

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

Segment Any 4D Gaussians

A generative world for general-purpose robotics & embodied AI learning.