This repository is a paper digest of recent advances in occupancy perception.
本仓库由公众号【自动驾驶之心】 团队整理，欢迎关注，一览最前沿的技术分享！
欢迎学习自动驾驶之心出品的 Occupancy从入门到精通全栈教程
InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction
[NeurIPS 2023] POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
UniVision: A Unified Framework for Vision-Centric 3D Perception
Fully Sparse 3D Panoptic Occupancy Prediction
[AAAI 2024] RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation
[AAAI 2024] Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving
OccNeRF: Self-Supervised Multi-Camera Occupancy Prediction with Neural Radiance Fields
Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications
DepthSSC: Depth-Spatial Alignment and Dynamic Voxel Resolution for Monocular 3D Semantic Scene Completion
OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving
Technical Report for Argoverse Challenges on 4D Occupancy Forecasting
SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin
SOccDPT: Semi-Supervised 3D Semantic Occupancy from Dense Prediction Transformers trained under memory constraints
EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection
LiDAR-based 4D Occupancy Completion and Forecasting
S4C: Self-Supervised Semantic Scene Completion with Neural Fields
Predicting Future Spatiotemporal Occupancy Grids with Semantics for Autonomous Driving
Scene Informer: Anchor-based Occlusion Inference and Trajectory Prediction in Partially Observable Environments
[ICRA2024] PointSSC: A Cooperative Vehicle-Infrastructure Point Cloud Benchmark for Semantic Scene Completion
OCC-VO: Dense Mapping via 3D Occupancy-Based Visual Odometry for Autonomous Driving
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving
RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision
OccupancyDETR: Making Semantic Scene Completion as Straightforward as Object Detection
[ITSC 2023] Connected Autonomous Vehicle Motion Planning with Video Predictions from Smart, Self-Supervised Infrastructure
PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction
[AAAI2024] SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection
[ICCV 2023] MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection
UniWorld: Autonomous Driving Pre-training via World Models
[IROS 2023] Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps
Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving
FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving
OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarios
CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion
Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's Eye View
[CVPR 2023 Challenge] FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation
[TIV] LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging Radar and Camera Fusion
Symphonize 3D Semantic Scene Completion with Contextual Instance Queries
[CVPR 2023 Challenge] Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challenge
[CVPR 2023 Challenge] UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering
UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction
Learning Occupancy for Monocular 3D Object Detection
[CVPR 2023] GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training
[ITSC 2023] Occupancy Prediction-Guided Neural Planner for Autonomous Driving
A Simple Framework for 3D Occupancy Estimation in Autonomous Driving
[ICCV 2023] OccNet: Scene as Occupancy
[IROS 2023] SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion
SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving
OVO: Open-Vocabulary Occupancy
PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation
BEVDet-Occ
Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction
BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy
Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
StereoScene: BEV-Assisted Stereo Matching Empowers 3D Semantic Scene Completion
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
[CVPR 2023] Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
[CVPR 2023] Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting
OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data
[ICRA 2023] StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks
[CVPR 2022] MonoScene: Monocular 3D Semantic Scene Completion
[ECCV 2022] Differentiable Raycasting for Self-supervised Occupancy Forecasting
LOPR: Latent Occupancy PRediction using Generative Models
[IROS 2022] Dynamics-Aware Spatiotemporal Occupancy Prediction in Urban Environments
STrajNet: Multi-modal Hierarchical Transformer for Occupancy Flow Field Prediction in Autonomous Driving
HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction
Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference
[IEEE Robotics and Automation Letters] Occupancy Flow Fields for Motion Forecasting in Autonomous Driving
[AAAI 2021] Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
[ CVPR 2020] 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
[CVPR 2020] Anisotropic Convolutional Networks for 3D Semantic Scene Completion
[3DV 2020] LMSCNet: Lightweight Multiscale 3D Semantic Completion
Semantic Scene Completion from a Single Depth Image
Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review
TorchSSC
OpenOcc
The-Eyes-Have-It
Autonomous Challenge Driving Track 3 3D Occupancy Prediction
清华大学&英伟达最新｜Occ3D：通用全面的大规模3D Occupancy预测基准
Occupancy Network综述！Grid-Centric的感知方法（BEV/多任务/轨迹预测等）
This repository was mainly written by Rujia Wang.
If you have any questions about the paper list, please do not hesitate to email me or open an issue on GitHub.
自动驾驶之心知识星球是过国内首个以自动驾驶技术栈为主线的交流学习社区（也是国内最大哦），这是一个前沿技术发布和学习的地方！我们汇总了自动驾驶感知（BEV、多模态感知、Occupancy、毫米波雷达视觉感知、车道线检测、3D感知、目标跟踪、多模态、多传感器融合、Transformer等）、自动驾驶定位建图（在线高精地图、高精地图、SLAM）、多传感器标定（Camera/Lidar/Radar/IMU等近20种方案）、Nerf、视觉语言模型、世界模型、规划控制、轨迹预测、领域技术方案、AI模型部署落地等几乎所有子方向的学习路线！
除此之外，还和数十家自动驾驶公司建立了内推渠道，简历直达！这里可以自由提问交流，许多算法工程师和硕博日常活跃，解决问题！初衷是希望能够汇集行业大佬的智慧，在学习和就业上帮到大家！星球的每周活跃度都在前50内，非常注重大家积极性的调度和讨论，欢迎加入一起成长！
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent