Skip to content
/ Awesome-Multi-Camera-3D-Occupancy-Prediction Public

Awesome papers and code about Multi-Camera 3D Occupancy Prediction, such as TPVFormer, SurroundOcc, PanoOcc, OccFormer, FB-OCC, SelfOcc, COTR, SparseOcc, GaussianFormer, GaussianOcc. In this repository, you will see the latest 3D occupancy prediction papers and code.

License

MIT license
102 stars 9 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

lvchuandong/Awesome-Multi-Camera-3D-Occupancy-Prediction

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
imgs
imgs
 
 
LICENSE
LICENSE
 
 
README.md
README.md
 
 

Repository files navigation

Awesome-Multi-Camera-3D-Occupancy-Prediction

CVPR

2024

  • [2024.05] DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving [paper]
  • [2024.04] SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction [paper] [github]
  • [2024.04] StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation [github]
  • [2024.04] Unsupervised Occupancy Learning from Sparse Point Cloud [paper]
  • [2024.03] SemCity: Semantic Scene Generation with Triplane Diffusion [paper] [github]
  • [2024.02] Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles [paper] [github]
  • [2023.12] Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications [paper] [github]
  • [2023.12] COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction [paper]
  • [2023.11] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction [paper] [github]
  • [2023.06] PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation [paper] [github]
  • [2023.06] Symphonize 3D Semantic Scene Completion with Contextual Instance Queries [paper] [github]
  • [2023.05] OccupancyM3D: Learning Occupancy for Monocular 3D Object Detection [paper] [github]
  • [2024] Accurate Training Data for Occupancy Map Prediction in Automated Driving using Evidence Theory
  • [2024] LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction
  • [2024] SGC-Occ: Semantic-Geometry Consistent 3D Occupancy Prediction for Autonomous Driving
  • [2024] UnO: Unsupervised Occupancy Fields for Perception and Forecasting [paper] [github]
  • [2024] Diffusion-FOF: Single-view Clothed Human Reconstruction via Diffusion-based Fourier Occupancy Field

2023

  • [2023.02] TPVFormer: Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction [paper] [github] [zhihu] [bilibili]
  • [2023.02] VoxFormer: a Cutting-edge Baseline for 3D Semantic Occupancy Prediction [paper] [github] [zhihu]
  • [2023.01] Behind the Scenes: Density Fields for Single View Reconstruction[paper] [github] [zhihu]
  • [2023.02] Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting [paper] [github]
  • [2022.12] UniAD: Planning-oriented Autonomous Driving [paper] [github]

2022

  • [2021.12] MonoScene: Monocular 3D Semantic Scene Completion [paper] [github] [zhihu]

ICCV

2023

  • [2023.04] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction [paper] [github]
  • [2023.03] SurroundOcc [paper] [github] [zhihu]

ECCV

2024

  • [2024.09] CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction [paper] [github]
  • [2024.09] RenderWorld: World Model with Self-Supervised 3D Label [paper]
  • [2024.07] Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [paper] [github]
  • [2024.07] VEON: Vocabulary-Enhanced Occupancy Prediction [paper]
  • [2024.07] Occupancy as Set of Points [paper] [github]
  • [2024.05] GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction [paper] [github]
  • [2024.05] ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers [paper] [github]
  • [2024.04] OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving [paper] [github]
  • [2023.12] Fully Sparse 3D Panoptic Occupancy Prediction [paper] [github]
  • [2023.11] OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving [paper] [github]

AAAI

2024

  • [2023.12] Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence [paper]
  • [2023.12] RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation [paper]
  • [2023.08] SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection [paper] [github]

Journal

  • [2024.09] OccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction [paper] [IEEE Transactions on Intelligent Vehicles]
  • [2024.06] HybridOcc: NeRF Enhanced Transformer-Based Multi-Camera 3D Occupancy Prediction [paper] [IEEE Robotics and Automation Letters]
  • [2024.03] Co-Occ: Coupling Explicit Feature Fusion With Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction [paper] [IEEE Robotics and Automation Letters]
  • [2024.02] Multi-Camera Unified Pre-Training via 3D Scene Reconstruction [paper] [IEEE Robotics and Automation Letters]
  • [2023.12] 3DOPFormer: 3D Occupancy Perception from Multi-Camera Images with Directional and Distance Enhancement [paper] [github] [IEEE Transactions on Intelligent Vehicles]

ICRA

2024

  • [2024.03] FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird’s-Eye View and Perspective View [paper]
  • [2024.03] MonoOcc: Digging into Monocular Semantic Occupancy Prediction [paper] [github]
  • [2023.09] RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision [paper] [github]

NeurIPS

2023

  • [2024.01] POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images [paper] [github] [website]
  • [2023.12] Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving [paper] [github] [website]

Arxiv

  • [2024.11] Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting [paper]
  • [2024.11] LeC2O-NeRF: Learning Continuous and Compact Large-Scale Occupancy for Urban Scenes [paper]
  • [2024.11] GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving [paper] [github]
  • [2024.11] Robust 3D Semantic Occupancy Prediction with Calibration-free Spatial Transformation [paper] [github]
  • [2024.11] ALOcc: Adaptive Lifting-based 3D Semantic Occupancy and Cost Volume-based Flow Prediction [paper] [github]
  • [2024.11] OccLoff: Learning Optimized Feature Fusion for 3D Occupancy Prediction [paper]
  • [2024.10] TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancement [paper] [github]
  • [2024.10] DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model [paper] [github]
  • [2024.10] DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes [paper] [github]
  • [2024.10] ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera [paper]
  • [2024.10] SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs [paper]
  • [2024.10] WildOcc: A Benchmark for Off-Road 3D Semantic Occupancy Prediction [paper] [github]
  • [2024.10] Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving [paper] [github]
  • [2024.09] OPUS: Occupancy Prediction Using a Sparse Set [paper] [github]
  • [2024.09] OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity [paper] [github]
  • [2024.09] FSF-Net: Enhance 4D Occupancy Forecasting with Coarse BEV Scene Flow for Autonomous Driving [paper]
  • [2024.09] ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning [paper]
  • [2024.09] DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction [paper] [github]
  • [2024.09] Deep Height Decoupling for Precise Vision-based 3D Occupancy Prediction [paper] [github]
  • [2024.09] UltimateDO: An Efficient Framework to Marry Occupancy Prediction with 3D Object Detection via Channel2height [paper]
  • [2024.09] Online Diffusion-Based 3D Occupancy Prediction at the Frontier with Probabilistic Map Reconciliation [paper]
  • [2024.09] OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving [paper]
  • [2024.08] AdaOcc: Adaptive-Resolution Occupancy Prediction [paper]
  • [2024.08] Diffusion-Occ: 3D Point Cloud Completion via Occupancy Diffusion [paper]
  • [2024.08] GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting [paper] [github]
  • [2024.08] MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive Reordering [paper] [github]
  • [2024.08] Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance [paper]
  • [2024.08] HybridOcc: NeRF Enhanced Transformer-based Multi-Camera 3D Occupancy Prediction [paper]
  • [2024.08] OccMamba: Semantic Occupancy Prediction with State Space Models [paper]
  • [2024.07] LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering [paper]
  • [2024.07] LiCROcc: Teach Radar for Accurate Semantic Occupancy Prediction using LiDAR and Camera [paper] [github]
  • [2024.07] Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction [paper] [github]
  • [2024.07] Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement [paper]
  • [2024.07] Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [paper] [github]
  • [2024.07] VEON: Vocabulary-Enhanced Occupancy Prediction [paper]
  • [2024.07] Occupancy as Set of Points [paper] [github]
  • [2024.06] EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy Network [paper]
  • [2024.05] GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction [paper] [github]
  • [2024.05] OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving [paper] [github]
  • [2024.05] BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network [paper]
  • [2024.05] RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar [paper]
  • [2024.05] Label-efficient Semantic Scene Completion with Scribble Annotations [paper]
  • [2024.05] Improving 3D Occupancy Prediction through Class-balancing Loss and Multi-scale Representation [paper]
  • [2024.05] ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers [paper] [github]
  • [2024.05] A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective [paper]
  • [2024.04] OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving [paper] [github]
  • [2024.04] OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks [paper]
  • [2024.04] SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction [paper] [github]
  • [2024.04] Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction [paper] [github] [website]
  • [2024.04] Unsupervised Occupancy Learning from Sparse Point Cloud [paper]
  • [2024.03] Urban Scene Diffusion through Semantic Occupancy Map [paper] [website]
  • [2024.03] MonoOcc: Digging into Monocular Semantic Occupancy Prediction [paper] [github]
  • [2024.03] Real-time 3D semantic occupancy prediction for autonomous vehicles using memory-efficient sparse convolution [paper]
  • [2024.03] UniLiDAR: Bridge the domain gap among different LiDARs for continual learning [paper]
  • [2024.03] OccFiner: Offboard Occupancy Refinement with Hybrid Propagation [paper]
  • [2024.03] Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception [paper] [github]
  • [2024.03] OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction [paper]
  • [2024.03] FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird’s-Eye View and Perspective View [paper]
  • [2024.03] OccFusion: A Straightforward and Effective Multi-Sensor Fusion Framework for 3D Occupancy Prediction [paper] [github]
  • [2024.02] OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction [paper]
  • [2024.02] OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flow [paper]
  • [2024.02] SDGE: Stereo Guided Depth Estimation for 360∘ Camera Sets [paper]
  • [2024.01] S2TPVFormer: Spatio-Temporal Tri-Perspective View for temporally coherent 3D Semantic Occupancy Prediction [paper]
  • [2024.01] InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction [paper] [github]
  • [2024.01] UniVision: A Unified Framework for Vision-Centric 3D Perception [paper] [github]
  • [2023.12] Fully Sparse 3D Panoptic Occupancy Prediction [paper] [github]
  • [2023.12] Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving [paper] [github]
  • [2023.12] RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation [paper]
  • [2023.12] OccNeRF: Self-Supervised Multi-Camera Occupancy Prediction with Neural Radiance Fields [paper] [github]
  • [2023.12] Camera-based 3D Semantic Scene Completion with Sparse Guidance Network [paper] [github]
  • [2023.12] OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries [paper] [github]
  • [2023.11] DepthSSC: Depth-Spatial Alignment and Dynamic Voxel Resolution for Monocular 3D Semantic Scene Completion [paper]
  • [2023.11] OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving [paper] [github]
  • [2023.11] Technical Report for Argoverse Challenges on 4D Occupancy Forecasting [paper]
  • [2023.10] LiDAR-based 4D Occupancy Completion and Forecasting [paper] [github]
  • [2023.11] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction [paper] [github]
  • [2023.11] SOccDPT: Semi-Supervised 3D Semantic Occupancy from Dense Prediction Transformers trained under memory constraints [paper]
  • [2023.11] FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin [paper] [github]
  • [2023.10] Predicting Future Spatiotemporal Occupancy Grids with Semantics for Autonomous Driving [paper]
  • [2023.09] OccupancyDETR: Making Semantic Scene Completion as Straightforward as Object Detection[paper]
  • [2023.09] OCC-VO: Dense Mapping via 3D Occupancy-Based Visual Odometry for Autonomous Driving [paper]
  • [2023.09] SPOT: Scalable 3D Pre-training via Occupancy Prediction for Autonomous Driving[paper]
  • [2023.09] RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision [paper] [github]
  • [2023.08] PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction [paper] [github]
  • [2023.07] OCTraN: 3D Occupancy Convolutional Transformer Network in Unstructured Traffic Scenarios [paper]
  • [2023.07] FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation [paper] [github]
  • [2023.06] PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation [paper] [github]
  • [2023.06] Symphonize 3D Semantic Scene Completion with Contextual Instance Queries [paper] [github]
  • [2023.06] UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering [paper]
  • [2023.05] OVO: Open-Vocabulary Occupancy [paper] [github]
  • [2023.05] Learning Occupancy for Monocular 3D Object Detection [paper] [github]
  • [2023.05] UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction [paper] [github]
  • [2023.04] OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction [paper] [github]
  • [2023.03] SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving [paper] [github]
  • [2023.03] OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception [paper] [github]
  • [2023.03] BEVDet for occupancy: [github]
  • [2023.03] SimpleOccupancy: A Simple Attempt for 3D Occupancy Estimation in Autonomous Driving [paper] [github]
  • [2023.02] OccDepth: A Depth-aware Method for 3D Semantic Occupancy Network [paper] [github]
  • [2023.02] TPVFormer: Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction [paper] [github] [zhihu] [bilibili]

Occupancy Datasets

  • [2023.06] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving [paper] [github]
  • [2023.06] Scene as Occupancy [paper] [github]
  • [2023.04] Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving [paper] [github]
  • [2023.03] OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception [paper] [github]
  • [2023.03] SurroundOcc [paper] [github]
  • Occupancy Dataset for nuScenes [github]
  • [2023.12] ML3DOP: A Multi-Camera and LiDAR Dataset for 3D Occupancy Perception[paper] [github]

Survey

  • [2024.05] A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective [paper] [github]
  • [2024.05] Vision-based 3D occupancy prediction in autonomous driving: a review and outlook [paper]
  • [2023.03] Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review [paper]

Pre-training

  • [2023.05] Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction [paper] [github]
  • [2022.06] Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders [paper] [github]

3D Occupancy Prediction Challenge

  • CVPR 2023 3D Occupancy Prediction Challenge: The world's First 3D Occupancy Benchmark for Scene Perception in Autonomous Driving [github] [website]
  • CVPR 2024 Autonomous Grand Challenge Occupancy and Flow [github] [website]

Tesla's Occupancy Networks

Blog

Code for Occupancy Generation

  • multi-frame fusion [github]
  • Poisson reconstruction [github]

Related Projects

About

Awesome papers and code about Multi-Camera 3D Occupancy Prediction, such as TPVFormer, SurroundOcc, PanoOcc, OccFormer, FB-OCC, SelfOcc, COTR, SparseOcc, GaussianFormer, GaussianOcc. In this repository, you will see the latest 3D occupancy prediction papers and code.

Topics

deep-learning autonomous-driving 3d-perception 3d-occupancy-prediction occupancy-perception

Resources

Readme

License

MIT license
Activity

Stars

102 stars

Watchers

4 watching

Forks

9 forks
Report repository

Releases

No releases published

Packages

No packages published