Matteo Poggi

32

Papers

149

Total Citations

Papers (32)

Beyond local reasoning for stereo confidence estimation with deep learning

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

Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions

Federated Online Adaptation for Deep Stereo

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

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

Guided Stereo Matching

Learning Monocular Depth Estimation Infusing Traditional Stereo Knowledge

Distilled Semantics for Comprehensive Scene Understanding from Videos

On the Uncertainty of Self-Supervised Monocular Depth Estimation

Learning Optical Flow From Still Images

Open Challenges in Deep Stereo: The Booster Dataset

RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation

NeRF-Supervised Deep Stereo

CompletionFormer: Depth Completion With Convolutions and Vision Transformers

Unsupervised Adaptation for Deep Stereo

Quantitative Evaluation of Confidence Measures in a Machine Learning World

Sensor-Guided Optical Flow

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

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

Learning Depth Estimation for Transparent and Mirror Surfaces

Active Stereo Without Pattern Projector

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

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

Self-adapting confidence estimation for stereo

Learning Temporally Consistent Video Depth from Video Diffusion Priors

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

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

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

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

Learning to Predict Stereo Reliability Enforcing Local Consistency of Confidence Maps

Real-Time Self-Adaptive Deep Stereo