一文看尽！3D占用预测近3年的主流工作有哪些？

点击下方卡片，关注“自动驾驶之心”公众号

戳我-> 领取自动驾驶近15个方向学习路线

>>点击进入→自动驾驶之心『占用网络』技术交流群

论文作者 | 自动驾驶Daily

编辑 | 自动驾驶之心

看到了一个repo，里面将近3年的3D-Occupancy-Prediction论文进行了汇总，这里也分享给大家，建议收藏！

重磅，我们最近的Occupancy数据生成与模型实战快要开课了，也欢迎大家加入学习：Occupancy数据生成与模型实战教程（戳我）

2024

CVPR 2024 (Accepted Papers)

• [Submitted 12 February, 2024] Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles [paper]

• [Submitted 7 December, 2023] Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications [paper] [code]

• [Submitted 4 December, 2023] COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction [paper]

• [Submitted 29 November, 2023] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction [paper] [code]

• [Submitted 16 June, 2023] PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation [paper] [code]

• [Submitted 25 May, 2023] Learning Occupancy for Monocular 3D Object Detection [paper] [code]

• StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation

• Accurate Training Data for Occupancy Map Prediction in Automated Driving using Evidence Theory

• LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction

• SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction

• SGC-Occ: Semantic-Geometry Consistent 3D Occupancy Prediction for Autonomous Driving

• Unsupervised Occupancy Learning from Sparse Point Cloud

• UnO: Unsupervised Occupancy Fields for Perception and Forecasting

Arxiv

• [Submitted 18 March, 2024] Urban Scene Diffusion through Semantic Occupancy Map [paper] [website]

• [Submitted 13 March, 2024] MonoOcc: Digging into Monocular Semantic Occupancy Prediction [paper] [code]

• [Submitted 13 March, 2024] Real-time 3D semantic occupancy prediction for autonomous vehicles using memory-efficient sparse convolution [paper]

• [Submitted 13 March, 2024] UniLiDAR: Bridge the domain gap among different LiDARs for continual learning [paper]

• [Submitted 13 March, 2024] OccFiner: Offboard Occupancy Refinement with Hybrid Propagation [paper]

• [Submitted 12 March, 2024] Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception [paper] [code]

• [Submitted 08 March, 2024] OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction [paper]

• [Submitted 05 March, 2024] FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird’s-Eye View and Perspective View [paper]

• [Submitted 03 March, 2024] OccFusion: A Straightforward and Effective Multi-Sensor Fusion Framework for 3D Occupancy Prediction [paper] [code]

• [Submitted 28 February, 2024] OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction [paper]

• [Submitted 20 February, 2024] OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flow [paper]

• [Submitted 19 February, 2024] SDGE: Stereo Guided Depth Estimation for 360∘ Camera Sets [paper]

• [Submitted 24 January, 2024] S2TPVFormer: Spatio-Temporal Tri-Perspective View for temporally coherent 3D Semantic Occupancy Prediction [paper]

• [Submitted 23 January, 2024] InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction [paper] [code]

• [Submitted 13 January, 2024] UniVision: A Unified Framework for Vision-Centric 3D Perception [paper] [code]

2023

CVPR 2023

• [Submitted 2 August, 2023] Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving [paper] [website]

• [Submitted 30 April, 2023] Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting [paper]

• [Submitted 25 March, 2023] VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion [paper] [code]

• [Submitted 13 March, 2023] SCPNet: Semantic scene completion on point cloud [paper]

• [Submitted 2 March, 2023] Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction [paper] [code]

ICCV 2023

• OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction [paper] [code]

• [Submitted 27 August, 2023] SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving [paper] [code]

• [Submitted 5 Jun, 2023] Scene as Occupancy [paper] [code]

• [Submitted 7 March, 2023] Openoccupancy: A large scale benchmark for surrounding semantic occupancy perception [paper] [code]

NIPS 2023

• [Submitted 17 January, 2024] POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images [paper] [code]

• [Submitted 13 December, 2023] Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving [paper] [code] [dataset download]

Arxiv

• [Submitted 28 December, 2023] Fully Sparse 3D Panoptic Occupancy Prediction [paper]

• [Submitted 19 December, 2023] Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving [paper] [code]

• [Submitted 19 December, 2023] RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation [paper]

• [Submitted 14 December, 2023] OccNeRF: Self-Supervised Multi-Camera Occupancy Prediction with Neural Radiance Fields [paper] [code]

• [Submitted 10 December, 2023] Camera-based 3D Semantic Scene Completion with Sparse Guidance Network [paper] [code]

• [Submitted 06 December, 2023] OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries [paper]

• [Submitted 28 November, 2023] DepthSSC: Depth-Spatial Alignment and Dynamic Voxel Resolution for Monocular 3D Semantic Scene Completion [paper]

• [Submitted 27 November, 2023] OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving [paper] [code]

• [Submitted 27 November, 2023] Technical Report for Argoverse Challenges on 4D Occupancy Forecasting [paper]

• [Submitted 19 November, 2023] SOccDPT: Semi-Supervised 3D Semantic Occupancy from Dense Prediction Transformers trained under memory constraints [paper]

• [Submitted 18 November, 2023] FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin [paper]

• [Submitted 17 October, 2023] LiDAR-based 4D Occupancy Completion and Forecasting [paper] [code]

• [Submitted 03 October, 2023] Predicting Future Spatiotemporal Occupancy Grids with Semantics for Autonomous Driving [paper]

• [Submitted 19 September, 2023] SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving [paper]

• [Submitted 18 September, 2023] RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision [paper] [code]

• [Submitted 15 September, 2023] OccupancyDETR: Making Semantic Scene Completion as Straightforward as Object Detection [paper] [code]

• [Submitted 31 August, 2023] PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction [paper] [code]

• [Submitted 26 August, 2023] SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection [paper] [code]

• [Submitted 14 August, 2023] UniWorld: Autonomous Driving Pre-training via World Models [paper] [code]

• [Submitted 20 July, 2023] OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarios [paper] [code]

• [Submitted 04 July, 2023] FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation [paper] [code]

• [Submitted June, 2023] MiLO: Multi-task Learning with Localization Ambiguity Suppression for Occupancy Prediction CVPR 2023 Occupancy Challenge Report [paper]

• [Submitted 27 June, 2023] Symphonize 3D Semantic Scene Completion with Contextual Instance Queries [paper] [code]

• [Submitted 20 June, 2023] Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challenge [paper]

• [Submitted 15 June, 2023] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving [paper] [code]

• [Submitted 15 June, 2023] UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering [paper]

• [Submitted 30 May, 2023] Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction [paper] [code]

• [Submitted 26 May, 2023] BEV-IO: Enhancing Bird’s-Eye-View 3D Detection with Instance Occupancy [paper]

• [Submitted 25 May, 2023] OVO: Open-Vocabulary Occupancy [paper] [code]

• [Submitted 05 May, 2023] Occupancy Prediction-Guided Neural Planner for Autonomous Driving [paper] [code]

• [Submitted 24 March, 2023] StereoScene: BEV-Assisted Stereo Matching Empowers 3D Semantic Scene Completion [paper] [code]

• [Submitted 24 March, 2023] Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion [paper]

• [Submitted 17 March, 2023] A Simple Attempt for 3D Occupancy Estimation in Autonomous Driving [paper] [code]

• [Submitted 27 February, 2023] OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion [paper] [code]

• [Submitted 19 February, 2023] FusionMotion: Multi-Sensor Asynchronous Fusion for Continuous Occupancy Prediction via Neural-ODE [paper]

ECCV 2022

• [Submitted 18 October, 2022] Differentiable Raycasting for Self-supervised Occupancy Forecasting [paper]

Survey

• [Submitted 2 March, 2023] Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review [paper]

Dataset

• [Submitted 13 December, 2023] Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving [paper] [code] [dataset download]

• [Submitted 29 September, 2023] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving [paper] [Github]

• [Submitted 27 August, 2023] SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving [paper] [Github]

• [Submitted 5 Jun, 2023] OpenScene: Scene as Occupancy [paper] [Github] [website]

• [Submitted 5 Jun, 2023] OccNet: Scene as Occupancy [paper] [Github]

• [Submitted 7 March, 2023] Openoccupancy: A large scale benchmark for surrounding semantic occupancy perception [paper] [Github]

• [Submitted 16 August, 2019] Semantickitti: A dataset for semantic scene understanding of lidar sequences [paper] [website]

• Occupancy Dataset for nuScenes [Github]

Challenge

• CVPR 2023 3D Occupancy Prediction Challenge [Github] [website]

• CVPR 2024 Autonomous Grand Challenge Occupancy and Flow [Github] [website]

投稿作者为『自动驾驶之心知识星球』特邀嘉宾，欢迎加入交流！

① 全网独家视频课程

BEV感知、BEV模型部署、BEV目标跟踪、毫米波雷达视觉融合、多传感器标定、多传感器融合、多模态3D目标检测、车道线检测、轨迹预测、在线高精地图、世界模型、点云3D目标检测、目标跟踪、Occupancy、cuda与TensorRT模型部署、大模型与自动驾驶、Nerf、语义分割、自动驾驶仿真、传感器部署、决策规划、轨迹预测等多个方向学习视频（扫码即可学习）

网页端官网：www.zdjszx.com

② 国内首个自动驾驶学习社区

国内最大最专业，近3000人的交流社区，已得到大多数自动驾驶公司的认可！涉及30+自动驾驶技术栈学习路线，从0到一带你入门自动驾驶感知（2D/3D检测、语义分割、车道线、BEV感知、Occupancy、多传感器融合、多传感器标定、目标跟踪）、自动驾驶定位建图（SLAM、高精地图、局部在线地图）、自动驾驶规划控制/轨迹预测等领域技术方案、大模型、端到端等，更有行业动态和岗位发布！欢迎扫描下方二维码，加入自动驾驶之心知识星球，这是一个真正有干货的地方，与领域大佬交流入门、学习、工作、跳槽上的各类难题，日常分享论文+代码+视频

③【自动驾驶之心】技术交流群

自动驾驶之心是首个自动驾驶开发者社区，聚焦感知、定位、融合、规控、标定、端到端、仿真、产品经理、自动驾驶开发、自动标注与数据闭环多个方向，目前近60+技术交流群，欢迎加入！

自动驾驶感知：目标检测、语义分割、BEV感知、毫米波雷达视觉融合、激光视觉融合、车道线检测、目标跟踪、Occupancy、深度估计、transformer、大模型、在线地图、点云处理、模型部署、CUDA加速等技术交流群；

多传感器标定：相机在线/离线标定、Lidar-Camera标定、Camera-Radar标定、Camera-IMU标定、多传感器时空同步等技术交流群；

多传感器融合：多传感器后融合技术交流群；

规划控制与预测：规划控制、轨迹预测、避障等技术交流群；

定位建图：视觉SLAM、激光SLAM、多传感器融合SLAM等技术交流群；

三维视觉：三维重建、NeRF、3D Gaussian Splatting技术交流群；

自动驾驶仿真：Carla仿真、Autoware仿真等技术交流群；

自动驾驶开发：自动驾驶开发、ROS等技术交流群；

其它方向：自动标注与数据闭环、产品经理、硬件选型、求职面试、自动驾驶测试等技术交流群；

扫码添加汽车人助理微信邀请入群，备注：学校/公司+方向+昵称（快速入群方式）

④【自动驾驶之心】硬件专场