Lorenzo Porzi

papers

1,065

total citations

papers (19)

The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale

ECCV 2020arXiv

citations

AutoRF: Learning 3D Object Radiance Fields From Single View Observations

CVPR 2022arXiv

citations

Learning Multi-Object Tracking and Segmentation From Automatic Annotations

CVPR 2020arXiv

citations

Towards Generalization Across Depth for Monocular 3D Object Detection

ECCV 2020arXiv

citations

MultiDiff: Consistent Novel View Synthesis from a Single Image

CVPR 2024arXiv

citations

Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?

ICCV 2021arXiv

citations

HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces

CVPR 2024arXiv

citations

Textured Gaussians for Enhanced 3D Scene Appearance Modeling

CVPR 2025arXiv

citations

Multi-Level Neural Scene Graphs for Dynamic Urban Environments

CVPR 2024arXiv

citations

Improving Panoptic Segmentation at All Scales

CVPR 2021arXiv

citations

ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing

CVPR 2024arXiv

citations

A Recipe for Generating 3D Worlds from a Single Image

ICCV 2025arXiv

citations

FlowR: Flowing from Sparse to Dense 3D Reconstructions

ICCV 2025arXiv

citations

Hardware-Rasterized Ray-Based Gaussian Splatting

CVPR 2025arXiv

citations

Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes

CVPR 2025arXiv

citations

Improving Optical Flow on a Pyramid Level

ECCV 2020arXiv

citations

Lorenzo Porzi

papers (19)

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

Panoptic Lifting for 3D Scene Understanding With Neural Fields

Revising Densification in Gaussian Splatting

The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale

AutoRF: Learning 3D Object Radiance Fields From Single View Observations

Learning Multi-Object Tracking and Segmentation From Automatic Annotations

Towards Generalization Across Depth for Monocular 3D Object Detection

MultiDiff: Consistent Novel View Synthesis from a Single Image

Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?

HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces

Textured Gaussians for Enhanced 3D Scene Appearance Modeling

Multi-Level Neural Scene Graphs for Dynamic Urban Environments

Improving Panoptic Segmentation at All Scales

ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing

A Recipe for Generating 3D Worlds from a Single Image

FlowR: Flowing from Sparse to Dense 3D Reconstructions

Hardware-Rasterized Ray-Based Gaussian Splatting

Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes

Improving Optical Flow on a Pyramid Level

papers (19)

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

Panoptic Lifting for 3D Scene Understanding With Neural Fields

Revising Densification in Gaussian Splatting

The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale

AutoRF: Learning 3D Object Radiance Fields From Single View Observations

Learning Multi-Object Tracking and Segmentation From Automatic Annotations

Towards Generalization Across Depth for Monocular 3D Object Detection

MultiDiff: Consistent Novel View Synthesis from a Single Image

Are We Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?

HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces

Textured Gaussians for Enhanced 3D Scene Appearance Modeling

Multi-Level Neural Scene Graphs for Dynamic Urban Environments

Improving Panoptic Segmentation at All Scales

ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing

A Recipe for Generating 3D Worlds from a Single Image

FlowR: Flowing from Sparse to Dense 3D Reconstructions

Hardware-Rasterized Ray-Based Gaussian Splatting

Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes

Improving Optical Flow on a Pyramid Level