GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction
Top Cited Papers
- 3 November 2024
- book chapter
- Published by Springer Nature
- p. 376-393
Abstract
No abstract availableKeywords
All Related Versions
This publication has 49 references indexed in Scilit:
- OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving2024
- Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis2024
- NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes2024
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- NeuMesh: Learning Disentangled Neural Mesh-Based Implicit Field for Geometry and Texture Editing2022
- Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D2020
- Atlas: End-to-End 3D Scene Reconstruction from Posed Images2020
- LMSCNet: Lightweight Multiscale 3D Semantic Completion2020
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009