SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

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

SemanticKITTI API for visualizing dataset, processing data, and evaluating results.

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

Seamless operability between C++11 and Python

[CVPR 2021] Self-supervised depth estimation from short sequences

[CVPR 2023] Multi-frame depth estimation in dynamic scenes. -- Li, Rui, et al. "Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes".

Official implementation of the paper: Behind the Scenes: Density Fields for Single View Reconstruction (CVPR 2023)

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

[ICCV 2023] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

iSLAM: Imperative SLAM (RA-L 2024) is a novel Visual-Inertial SLAM using Self-supervised Learning

[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation

A latent text-to-image diffusion model

Training library for local feature detection and matching

Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting

[TPAMI'23] Unifying Flow, Stereo and Depth Estimation

A toolbox for mapping and localization with line features.

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

🆓免费的 ChatGPT 镜像网站列表，持续更新。List of free ChatGPT mirror sites, continuously updated.

精益副业：程序员如何优雅地做副业

✨ Local and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

[CVPR 2023] PVO: Panoptic Visual Odometry

The official repository of our CVPR2023 paper "A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization".

自动驾驶笔记，以解析各模块知识点、整合行业优秀解决方案进行阐述，以帮助自己及有需要的读者；包含深度学习、deeplearning、无人驾驶、BEV、Transformer、ADAS、CVPR、特斯拉AI DAY、大模型、chatgpt等内容.

方糖全栈路线图2023，为「从螺丝钉到一人企业」补全技能栈