[Arxiv 2024] 🚀 🚀 🚀 The official implementation of NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation

Official repository for "Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders"

[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

[CVPR 2024] Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

Blender plugin which generates a dataset for colmap by exporting blender camera poses and rendering scene.

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

Project page of the paper: "Event-based Mosaicing Bundle Adjustment"

This is the implementation of paper Cinematic Gaussians:  Real-Time HDR Radiance Fields with Depth of Field

[arXiv 2024] Code for Deformable Radial Kernel Splatting

Official implementation of the paper "Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content".

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) fo…

Open source implementation of CVPR 2020 "Video to Events: Recycling Video Dataset for Event Cameras"

Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)

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.

Collection of event based vision utility functions

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

[arXiv 2024] Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video

[ARXIV'24] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

[CVPR 2024 Highlight] OpenESS: Event-Based Semantic Scene Understanding with Open Vocabularies

[WACV 2025] Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding

The official implementation of "Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis"

【AAAI2025】DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification

【AAAI2025】MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt

You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-Identification（AAAI2025）