Matteo Poggi

papers

1,243

total citations

papers (25)

Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation

ECCV 2020arXiv

citations

Open Challenges in Deep Stereo: The Booster Dataset

CVPR 2022arXiv

citations

Learning Optical Flow From Still Images

CVPR 2021arXiv

citations

Learning Depth Estimation for Transparent and Mirror Surfaces

ICCV 2023arXiv

citations

Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

CVPR 2025arXiv

citations

Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions

ECCV 2024arXiv

citations

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

ICCV 2023arXiv

citations

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

ECCV 2022arXiv

citations

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

ICCV 2023arXiv

citations

Federated Online Adaptation for Deep Stereo

CVPR 2024arXiv

citations

Active Stereo Without Pattern Projector

ICCV 2023arXiv

citations

RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation

CVPR 2022arXiv

citations

Self-adapting confidence estimation for stereo

ECCV 2020arXiv

citations

Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation

CVPR 2025arXiv

citations

Sensor-Guided Optical Flow

ICCV 2021arXiv

citations

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases

ICCV 2025arXiv

citations

ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration

ICCV 2025arXiv

citations

Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation

ICCV 2025arXiv

citations

Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond

ICCV 2025arXiv

citations

Matteo Poggi

papers (25)

On the Uncertainty of Self-Supervised Monocular Depth Estimation

GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction

CompletionFormer: Depth Completion With Convolutions and Vision Transformers

Learning Temporally Consistent Video Depth from Video Diffusion Priors

Distilled Semantics for Comprehensive Scene Understanding from Videos

NeRF-Supervised Deep Stereo

Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation

Open Challenges in Deep Stereo: The Booster Dataset

Learning Optical Flow From Still Images

Learning Depth Estimation for Transparent and Mirror Surfaces

Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

Federated Online Adaptation for Deep Stereo

Active Stereo Without Pattern Projector

RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation

Self-adapting confidence estimation for stereo

Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation

Sensor-Guided Optical Flow

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases

ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration

Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation

Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond

papers (25)

On the Uncertainty of Self-Supervised Monocular Depth Estimation

GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction

CompletionFormer: Depth Completion With Convolutions and Vision Transformers

Learning Temporally Consistent Video Depth from Video Diffusion Priors

Distilled Semantics for Comprehensive Scene Understanding from Videos

NeRF-Supervised Deep Stereo

Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation

Open Challenges in Deep Stereo: The Booster Dataset

Learning Optical Flow From Still Images

Learning Depth Estimation for Transparent and Mirror Surfaces

Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

Federated Online Adaptation for Deep Stereo

Active Stereo Without Pattern Projector

RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation

Self-adapting confidence estimation for stereo

Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation

Sensor-Guided Optical Flow

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases

ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration

Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation

Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond