Awesome-Implicit-NeRF-Robotics

Awesome-Implicit-NeRF-Robotics

机器人领域中神经隐式表示和NeRF技术的最新进展

这个项目汇集了神经隐式表示和NeRF在机器人领域的应用论文,涵盖物体姿态估计、SLAM、操作学习、物体重建、物理模拟和导航规划等方向。它为研究人员和工程师提供了解该交叉领域最新进展的综合资源。

NeRF机器人SLAM姿态估计3D重建Github开源项目

Awesome-Implicit-NeRF-Robotics Awesome

This repo contains a curative list of Implicit Representations and NeRF papers relating to Robotics/RL domain, inspired by awesome-computer-vision <br>

Please feel free to send me pull requests or email to add papers! <br>

If you find this repository useful, please consider citing and STARing this list. Feel free to share this list with others!

For an overview of NeRFs, checkout the Survey (Neural Volume Rendering: NeRF And Beyond), Blog post (NeRF Explosion 2020) and Collection (awesome-NeRF)


Overview


Object Pose Estimation

  • BundleSDF: "Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects", CVPR, 2023. [Paper] [Webpage]

  • ShAPO: "Implicit Representations for Multi Object Shape Appearance and Pose Optimization", ECCV, 2022. [Paper] [Pytorch Code] [Webpage] [Video]

  • NCF: "Neural Correspondence Field for Object Pose Estimation", ECCV, 2022. [Paper] [Pytorch Code] [Webpage]

  • Neural-Sim: "Learning to Generate Training Data with NeRF", ECCV 2022. [Paper] [Pytorch Code] [Webpage]

  • DISP6D: "Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation", ECCV 2022. [Paper] [Pytorch Code] [Webpage] [Video]

  • SNAKE: "SNAKE: Shape-aware Neural 3D Keypoint Field", NeurIPS, 2022. [Paper] [Pytorch Code]

  • NeRF-RPN: "A general framework for object detection in NeRFs", CVPR 2023. [Paper] [Video]

  • NeRF-MAE: "Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields", ECCV 2024. [Paper] [Webpage] [Pytorch Code]

  • nerf2nerf: "Pairwise Registration of Neural Radiance Fields", arXiv. [Paper] [Pytorch Code] [Webpage] [Dataset]

  • iNeRF: "Inverting Neural Radiance Fields for Pose Estimation", IROS, 2021. [Paper] [Pytorch Code] [Website] [Dataset]

  • NeRF-Pose: "A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation", arXiv. [Paper]

  • PixTrack: "Precise 6DoF Object Pose Tracking using NeRF Templates and Feature-metric Alignment", arXiv. [Paper] [Pytorch Code]

  • "Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation", arXiv. [Paper] [Website]

  • NARF22: "Neural Articulated Radiance Fields for Configuration-Aware Rendering", IROS, 2022. [Paper] [Website]

  • FroDO: "From Detections to 3D Objects", CVPR, 2020. [Paper]

  • SDFEst: "Categorical Pose and Shape Estimation of Objects From RGB-D Using Signed Distance Fields", RA-L, 2022. [Paper] [Pytorch Code]

  • SSC-6D: "Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation", AAAI, 2022. [Paper] [Pytorch Code]

  • Style2NeRF: "An Unsupervised One-Shot NeRF for Semantic 3D Reconstruction", BMVC, 2022. [Paper]

  • "Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion", CVPR, 2023. [Paper] [Code]

  • TexPose: "Neural Texture Learning for Self-Supervised 6D Object Pose Estimation", CVPR 2023. [Paper][Code]

  • Canonical Fields: "Self-Supervised Learning of Pose-Canonicalized Neural Fields", arXiv. [Paper]

  • NeRF-Det: "Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection", arXiv. [Paper] [[Page] https://chenfengxu714.github.io/nerfdet/] [[Code] https://github.com/facebookresearch/NeRF-Det]

  • One-step NeRF: "Marrying NeRF with Feature Matching for One-step Pose Estimation", ICRA, 2024. [Paper] [Short Video] [[Website&Code] Coming]


SLAM

  • iSDF: "Real-Time Neural Signed Distance Fields for Robot Perception", RSS, 2022. [Paper] [Pytorch Code] [Website]

  • LENS: "LENS: Localization enhanced by NeRF synthesis", CORL, 2021. [Paper]

  • NICE-SLAM: "Neural Implicit Scalable Encoding for SLAM", CVPR, 2021. [Paper] Pytorch Code] [Website]

  • iMAP: "Implicit Mapping and Positioning in Real-Time", ICCV, 2021. [Paper] [Website]

  • BNV-Fusion: "BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion", CVPR, 2022. [Paper] Pytorch Code]

  • NeRF-SLAM: "Real-Time Dense Monocular SLAM with Neural Radiance Fields", arXiv. [Paper]

  • NICER-SLAM: "Neural Implicit Scene Encoding for RGB SLAM", arXiv. [Paper] [Video]

  • Nerfels: "Renderable Neural Codes for Improved Camera Pose Estimation", CVPR 2022 Workshop. [Paper]

  • GO-Surf: "A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mapping", 3DV, 2022. [Paper] [[Website(https://jingwenwang95.github.io/go_surf/)] [Pytorch Code]

  • Orbeez-SLAM: "Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction", arXiv, 2022. [Paper]

  • ESLAM: "Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields", arXiv, 2022. [Paper]

  • Panoptic Multi-TSDFs: "a Flexible Representation for Online Multi-resolution Volumetric Mapping and Long-term Dynamic Scene Consistency", ICRA, 2022. [Paper] [Pytorch Code]

  • SHINE-Mapping: "Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations", ICRA, 2023. [Paper] [Code]

  • "SDF-based RGB-D Camera Tracking in Neural Scene Representations", ICRA Workshop, 2022. [Paper]

  • Loc-NeRF: "Monte Carlo Localization using Neural Radiance Fields", ICRA, 2023. [Paper] [Code] [Video]

  • Vox-Fusion: "Dense Tracking and Mapping with Voxel-based Neural Implicit Representation", ISMAR, 2022. [Paper] [Website] [Pytorch Code] [Video]

  • NodeSLAM: "Dense Tracking and Mapping with Voxel-based Neural Implicit Representation", 3DV, 2020. [Paper]

  • iLabel: "Revealing Objects in Neural Fields", RA-L, 2023. [Paper]

  • Nerf–: "Neural radiance fields without known camera parameters", arXiv. [Paper]

  • L2G-NeRF: "Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields", CVPR, 2023. [Paper] [Website] [code]

  • H2-Mapping: "Real-time Dense Mapping Using Hierarchical Hybrid Representation", RA-L, 2023. [Paper] [code]

  • Continual Neural Mapping: "Learning An Implicit Scene Representation from Sequential Observations", ICCV, 2021. [Paper]

  • LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF, ICRA, 2023. [Paper] [Pytorch Code]

  • "Dense RGB SLAM with neural implicit maps", ICLR, 2023. [Paper]

  • NOCaL: Calibration-free semi-supervised learning of odometry and camera intrinsics, ICRA, 2023. [Paper] [Website]

  • IRMCL: Implicit Representation-based Online Global Localization, arXiv. [Paper] [Code]

  • Efficient Implicit Neural Reconstruction Using LiDAR, ICRA, 2023. [Paper] [Website] [Pytorch Code] [Video]

  • vMAP: "Vectorised Object Mapping for Neural Field SLAM", CVPR, 2023. [Paper] [Website]

  • "An Algorithm for the SE(3)-Transformation on Neural Implicit Maps for Remapping Functions", RA-L, 2022. [Paper]

  • "Implicit Object Reconstruction With Noisy Data", RSS Workshop, 2021. [Paper]

  • NeuSE: "Neural SE(3)-Equivariant Embedding for Consistent Spatial Understanding with Objects", arXiv. [Paper] [Website]

  • ObjectFusion: "Accurate object-level SLAM with neural object priors", Graphical Models, 2022. [Paper]

编辑推荐精选

材料星

材料星

专业的AI公文写作平台,公文写作神器

AI 材料星,专业的 AI 公文写作辅助平台,为体制内工作人员提供高效的公文写作解决方案。拥有海量公文文库、9 大核心 AI 功能,支持 30 + 文稿类型生成,助力快速完成领导讲话、工作总结、述职报告等材料,提升办公效率,是体制打工人的得力写作神器。

openai-agents-python

openai-agents-python

OpenAI Agents SDK,助力开发者便捷使用 OpenAI 相关功能。

openai-agents-python 是 OpenAI 推出的一款强大 Python SDK,它为开发者提供了与 OpenAI 模型交互的高效工具,支持工具调用、结果处理、追踪等功能,涵盖多种应用场景,如研究助手、财务研究等,能显著提升开发效率,让开发者更轻松地利用 OpenAI 的技术优势。

Hunyuan3D-2

Hunyuan3D-2

高分辨率纹理 3D 资产生成

Hunyuan3D-2 是腾讯开发的用于 3D 资产生成的强大工具,支持从文本描述、单张图片或多视角图片生成 3D 模型,具备快速形状生成能力,可生成带纹理的高质量 3D 模型,适用于多个领域,为 3D 创作提供了高效解决方案。

3FS

3FS

一个具备存储、管理和客户端操作等多种功能的分布式文件系统相关项目。

3FS 是一个功能强大的分布式文件系统项目,涵盖了存储引擎、元数据管理、客户端工具等多个模块。它支持多种文件操作,如创建文件和目录、设置布局等,同时具备高效的事件循环、节点选择和协程池管理等特性。适用于需要大规模数据存储和管理的场景,能够提高系统的性能和可靠性,是分布式存储领域的优质解决方案。

TRELLIS

TRELLIS

用于可扩展和多功能 3D 生成的结构化 3D 潜在表示

TRELLIS 是一个专注于 3D 生成的项目,它利用结构化 3D 潜在表示技术,实现了可扩展且多功能的 3D 生成。项目提供了多种 3D 生成的方法和工具,包括文本到 3D、图像到 3D 等,并且支持多种输出格式,如 3D 高斯、辐射场和网格等。通过 TRELLIS,用户可以根据文本描述或图像输入快速生成高质量的 3D 资产,适用于游戏开发、动画制作、虚拟现实等多个领域。

ai-agents-for-beginners

ai-agents-for-beginners

10 节课教你开启构建 AI 代理所需的一切知识

AI Agents for Beginners 是一个专为初学者打造的课程项目,提供 10 节课程,涵盖构建 AI 代理的必备知识,支持多种语言,包含规划设计、工具使用、多代理等丰富内容,助您快速入门 AI 代理领域。

AEE

AEE

AI Excel全自动制表工具

AEE 在线 AI 全自动 Excel 编辑器,提供智能录入、自动公式、数据整理、图表生成等功能,高效处理 Excel 任务,提升办公效率。支持自动高亮数据、批量计算、不规则数据录入,适用于企业、教育、金融等多场景。

UI-TARS-desktop

UI-TARS-desktop

基于 UI-TARS 视觉语言模型的桌面应用,可通过自然语言控制计算机进行多模态操作。

UI-TARS-desktop 是一款功能强大的桌面应用,基于 UI-TARS(视觉语言模型)构建。它具备自然语言控制、截图与视觉识别、精确的鼠标键盘控制等功能,支持跨平台使用(Windows/MacOS),能提供实时反馈和状态显示,且数据完全本地处理,保障隐私安全。该应用集成了多种大语言模型和搜索方式,还可进行文件系统操作。适用于需要智能交互和自动化任务的场景,如信息检索、文件管理等。其提供了详细的文档,包括快速启动、部署、贡献指南和 SDK 使用说明等,方便开发者使用和扩展。

Wan2.1

Wan2.1

开源且先进的大规模视频生成模型项目

Wan2.1 是一个开源且先进的大规模视频生成模型项目,支持文本到图像、文本到视频、图像到视频等多种生成任务。它具备丰富的配置选项,可调整分辨率、扩散步数等参数,还能对提示词进行增强。使用了多种先进技术和工具,在视频和图像生成领域具有广泛应用前景,适合研究人员和开发者使用。

爱图表

爱图表

全流程 AI 驱动的数据可视化工具,助力用户轻松创作高颜值图表

爱图表(aitubiao.com)就是AI图表,是由镝数科技推出的一款创新型智能数据可视化平台,专注于为用户提供便捷的图表生成、数据分析和报告撰写服务。爱图表是中国首个在图表场景接入DeepSeek的产品。通过接入前沿的DeepSeek系列AI模型,爱图表结合强大的数据处理能力与智能化功能,致力于帮助职场人士高效处理和表达数据,提升工作效率和报告质量。

下拉加载更多