Efficient Hybrid Scene Representation for Autonomous Driving: Lightning NeRF
Lightning NeRF introduces an efficient hybrid scene representation that leverages LiDAR data, improving novel view synthesis quality and rendering speed significantly.
Thermal-NeRF: Neural Radiance Fields from Infrared Camera for 3D Scene Reconstruction
Thermal-NeRF introduces a method to estimate NeRF solely from IR imaging, outperforming RGB-based methods in visually degraded scenes.
SpikeNeRF: Learning Neural Radiance Fields from Spike Camera Data
SpikeNeRF introduces a novel approach to deriving volumetric scene representations from spike camera data using NeRF, addressing challenges in real-world scenarios.
H2O-SDF: Two-Phase Learning for 3D Indoor Reconstruction
新しい二段階学習アプローチ、H2O-SDFは、屋内シーンの全体的なジオメトリを再構築し、色と法線情報の衝突を解決します。
SpikeNeRF: Learning Neural Radiance Fields from Spike Cameras
SpikeNeRFは、スパイクカメラからのニューラル放射輝度場学習を可能にする初の手法です。
InfNeRF: Large-Scale Scene Reconstruction with LoD Octree Structure
Efficient large-scale scene rendering using an LoD octree structure.
InfNeRF: Efficient Large-Scale Scene Rendering with O(log n) Space Complexity
InfNeRF introduces an innovative approach to large-scale scene rendering using Neural Radiance Fields and octree structures, achieving efficient rendering with reduced memory footprint.
Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes
Innovative Entity-NeRF method effectively removes moving objects and reconstructs static urban backgrounds.
CVT-xRF: Contrastive In-Voxel Transformer for 3D Radiance Fields from Sparse Inputs
提案されたCVT-xRFは、3D空間の一貫性を向上させるために新しいアプローチを提供します。
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
InsertNeRF introduces a novel paradigm by utilizing HyperNet modules to instill generalizability into NeRF, enhancing scene-specific representations and improving performance.
