NeRF Papers on Autonomous driving.

papers

• papers
  • 2021
  • 2022
  • 2023
  • 2024
• Other
• Codebase

2021

Neural Scene Graphs for Dynamic Scenes

[paper] [code] [project page]

method

MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis

[paper] [code] [project page]

method

2022

Block-NeRF: Scalable Large Scene Neural View Synthesis

[paper] [project page]

method

Urban Radiance Fields

[paper] [project page]

method

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

[paper]

method

Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

[paper] [code] [project page]

method

S-NeRF: Neural Radiance Fields for Street Views

[paper] [code] [project page]

method

2023

PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes

[paper] [code] [project page]

method

F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories

[paper] [code] [project page]

method

StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views

[paper] [code] [project page]

method

UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering

[paper]

method

UniSim: A Neural Closed-Loop Sensor Simulator

[paper] [project page]

method

MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving

[paper] [code] [project page]

method

Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering

[paper] [code] [project page]

method

MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection

[paper] [code]

method

SceneRF Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields

[paper] [code] [project page]

method

Urban Radiance Field Representation with Deformable Neural Mesh Primitives

[paper] [code] [project page]

method

NeuRAD: Neural Rendering for Autonomous Driving

[paper] [code] [project page]

method

RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision

[paper] [code]

method

UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video

[paper] [code] [project page]

method

NFL: Neural LiDAR Fields for Novel View Synthesis

[paper] [project page]

method

NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields

[paper]

method

LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields

[paper] [code] [project page]

method

Neural Fields meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes

[paper] [project page]

method

3D Data Augmentation for Driving Scenes on Camera

[paper]

method

PlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Urban Scene Reconstruction

[paper]

method

Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision

[paper] [project page]

method

SUDS: Scalable Urban Dynamic Scenes

[paper] [code] [project page]

method

CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations

[paper]

method

MV-Map: Offboard HD Map Generation with Multi-view Consistency

[paper]

method

PointNeRF++: A multi-scale, point-based Neural Radiance Field

[paper] [project page]

method

UC-NeRF: Neural Radiance Field for Under-Calibrated Multi-view Cameras in Autonomous Driving

[paper] [project page] [code]

method

DGNR: Density-Guided Neural Point Rendering of Large Driving Scenes

[paper]

method

SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields

[paper]

method

DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

[paper] [project page] [code(coming soon)]

method

LightSim: Neural Lighting Simulation for Urban Scenes

[paper] [project page]

method

OccNeRF: Self-Supervised Multi-Camera Occupancy Prediction with Neural Radiance Fields

[paper] [code] [project page]

method

ProSGNeRF: Progressive Dynamic Neural Scene Graph with Frequency Modulated Auto-Encoder in Urban Scenes

[paper] [code(not yet)]

method

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

[paper] [code] [project page]

method

MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond

[paper] [code] [project page]

method

OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous Driving

[paper] [code] [project page]

method

EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

[paper] [code] [project page]

method

2024

PC-NeRF: Parent-Child Neural Radiance Fields under Partial Sensor Data Loss in Autonomous Driving Environments

[paper] [code]

method

NeRFmentation: NeRF-based Augmentation for Monocular Depth Estimation

[paper]

method

Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving

[paper] [code]

method

RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes

[paper]

method

UPNeRF: A Unified Framework for Monocular 3D Object Reconstruction and Pose Estimation

[paper] [code] [project page]

method

LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis

[paper] [code] [project page]

method

S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation

[paper]

method

NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving

[paper] [code] [project page]

method

NeRF2Points: Large-Scale Point Cloud Generation From Street Views’ Radiance Field Optimization

[paper]

method

INPC: Implicit Neural Point Clouds for Radiance Field Rendering

[paper] [code] [project page]

method

Other

Awesome nerf

NeRF papers relating to Robotics/RL domain

NeRF papers relating to SLAM/Robotics domain

Codebase

NeRF(Jax)

NeRF(pytorch)

NeRF(pytorch_lighting)

instantNGP

NerfStudio: A collaboration friendly studio for NeRFs

NeRF-Factory: An awesome PyTorch NeRF collection

MultiNeRF: A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

XRNeRF: PyTorch-based codebase for Neural Radiance Field

sdfstudio: A unified framework for surface reconstruction

threestudio: A unified framework for 3D content creation