1 code implementation • 5 Dec 2024 • Luca Bartolomei, Fabio Tosi, Matteo Poggi, Stefano Mattoccia
We introduce Stereo Anywhere, a novel stereo-matching framework that combines geometric constraints with robust priors from monocular depth Vision Foundation Models (VFMs).
1 code implementation • 21 Nov 2024 • Xianda Guo, Chenming Zhang, Youmin Zhang, Dujun Nie, Ruilin Wang, Wenzhao Zheng, Matteo Poggi, Long Chen
To further enrich the model's ability to generalize across different conditions, we introduce a novel synthetic dataset that complements existing data by adding variability in baselines, camera angles, and scene types.
no code implementations • 12 Sep 2024 • Andrea Conti, Matteo Poggi, Valerio Cambareri, Stefano Mattoccia
High frame rate and accurate depth estimation plays an important role in several tasks crucial to robotics and automotive perception.
no code implementations • 11 Sep 2024 • Sadra Safadoust, Fabio Tosi, Fatma Güney, Matteo Poggi
3D Gaussian Splatting (GS) significantly struggles to accurately represent the underlying 3D scene geometry, resulting in inaccuracies and floating artifacts when rendering depth maps.
1 code implementation • 8 Aug 2024 • Luca Bartolomei, Matteo Poggi, Andrea Conti, Stefano Mattoccia
Event stereo matching is an emerging technique to estimate depth from neuromorphic cameras; however, events are unlikely to trigger in the absence of motion or the presence of large, untextured regions, making the correspondence problem extremely challenging.
1 code implementation • 23 Jul 2024 • Fabio Tosi, Pierluigi Zama Ramirez, Matteo Poggi
We present a novel approach designed to address the complexities posed by challenging, out-of-distribution data in the single-image depth estimation task.
1 code implementation • 10 Jul 2024 • Fabio Tosi, Luca Bartolomei, Matteo Poggi
Stereo matching is close to hitting a half-century of history, yet witnessed a rapid evolution in the last decade thanks to deep learning.
1 code implementation • 28 Jun 2024 • Xianda Guo, Chenming Zhang, Youmin Zhang, Wenzhao Zheng, Dujun Nie, Matteo Poggi, Long Chen
We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the matching process.
1 code implementation • 6 Jun 2024 • Luca Bartolomei, Matteo Poggi, Fabio Tosi, Andrea Conti, Stefano Mattoccia
This paper presents a novel general-purpose stereo and depth data fusion paradigm that mimics the active stereo principle by replacing the unreliable physical pattern projector with a depth sensor.
no code implementations • 3 Jun 2024 • Jiahao Shao, Yuanbo Yang, HongYu Zhou, Youmin Zhang, Yujun Shen, Vitor Guizilini, Yue Wang, Matteo Poggi, Yiyi Liao
Moreover, we design an effective training strategy to provide context within a clip.
no code implementations • CVPR 2024 • Matteo Poggi, Fabio Tosi
We introduce a novel approach for adapting deep stereo networks in a collaborative manner.
no code implementations • 16 May 2024 • Xin Qiao, Matteo Poggi, Pengchao Deng, Hao Wei, Chenyang Ge, Stefano Mattoccia
Integrating an RGB camera into a ToF imaging system has become a significant technique for perceiving the real world.
no code implementations • 25 Apr 2024 • Jaime Spencer, Fabio Tosi, Matteo Poggi, Ripudaman Singh Arora, Chris Russell, Simon Hadfield, Richard Bowden, Guangyuan Zhou, Zhengxin Li, Qiang Rao, Yiping Bao, Xiao Liu, Dohyeong Kim, Jinseong Kim, Myunghyun Kim, Mykola Lavreniuk, Rui Li, Qing Mao, Jiang Wu, Yu Zhu, Jinqiu Sun, Yanning Zhang, Suraj Patni, Aradhye Agarwal, Chetan Arora, Pihai Sun, Kui Jiang, Gang Wu, Jian Liu, Xianming Liu, Junjun Jiang, Xidan Zhang, Jianing Wei, Fangjun Wang, Zhiming Tan, Jiabao Wang, Albert Luginov, Muhammad Shahzad, Seyed Hosseini, Aleksander Trajcevski, James H. Elder
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC).
1 code implementation • 20 Feb 2024 • Fabio Tosi, Youmin Zhang, Ziren Gong, Erik Sandström, Stefano Mattoccia, Martin R. Oswald, Matteo Poggi
Over the past two decades, research in the field of Simultaneous Localization and Mapping (SLAM) has undergone a significant evolution, highlighting its critical role in enabling autonomous exploration of unknown environments.
1 code implementation • 25 Jan 2024 • Andrea Conti, Matteo Poggi, Valerio Cambareri, Stefano Mattoccia
Methods for 3D reconstruction from posed frames require prior knowledge about the scene metric range, usually to recover matching cues along the epipolar lines and narrow the search range.
1 code implementation • 14 Dec 2023 • Luca Bartolomei, Matteo Poggi, Andrea Conti, Fabio Tosi, Stefano Mattoccia
This paper proposes a new framework for depth completion robust against domain-shifting issues.
1 code implementation • ICCV 2023 • Chaoqiang Zhao, Matteo Poggi, Fabio Tosi, Lei Zhou, Qiyu Sun, Yang Tang, Stefano Mattoccia
This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture.
1 code implementation • ICCV 2023 • Luca Bartolomei, Matteo Poggi, Fabio Tosi, Andrea Conti, Stefano Mattoccia
This paper proposes a novel framework integrating the principles of active stereo in standard passive camera systems without a physical pattern projector.
1 code implementation • ICCV 2023 • Youmin Zhang, Fabio Tosi, Stefano Mattoccia, Matteo Poggi
Neural implicit representations have recently demonstrated compelling results on dense Simultaneous Localization And Mapping (SLAM) but suffer from the accumulation of errors in camera tracking and distortion in the reconstruction.
1 code implementation • 27 Aug 2023 • Giovanni Minelli, Matteo Poggi, Samuele Salti
In this paper, we tackle the problem of generating a novel image from an arbitrary viewpoint given a single frame as input.
1 code implementation • ICCV 2023 • Alex Costanzino, Pierluigi Zama Ramirez, Matteo Poggi, Fabio Tosi, Stefano Mattoccia, Luigi Di Stefano
Inferring the depth of transparent or mirror (ToM) surfaces represents a hard challenge for either sensors, algorithms, or deep networks.
1 code implementation • ICCV 2023 • Marc Botet Colomer, Pier Luigi Dovesi, Theodoros Panagiotakopoulos, Joao Frederico Carvalho, Linus Härenstam-Nielsen, Hossein Azizpour, Hedvig Kjellström, Daniel Cremers, Matteo Poggi
The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events.
no code implementations • 14 Apr 2023 • Jaime Spencer, C. Stella Qian, Michaela Trescakova, Chris Russell, Simon Hadfield, Erich W. Graf, Wendy J. Adams, Andrew J. Schofield, James Elder, Richard Bowden, Ali Anwar, Hao Chen, Xiaozhi Chen, Kai Cheng, Yuchao Dai, Huynh Thai Hoa, Sadat Hossain, Jianmian Huang, Mohan Jing, Bo Li, Chao Li, Baojun Li, Zhiwen Liu, Stefano Mattoccia, Siegfried Mercelis, Myungwoo Nam, Matteo Poggi, Xiaohua Qi, Jiahui Ren, Yang Tang, Fabio Tosi, Linh Trinh, S. M. Nadim Uddin, Khan Muhammad Umair, Kaixuan Wang, YuFei Wang, Yixing Wang, Mochu Xiang, Guangkai Xu, Wei Yin, Jun Yu, Qi Zhang, Chaoqiang Zhao
This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC).
2 code implementations • CVPR 2023 • Fabio Tosi, Alessio Tonioni, Daniele De Gregorio, Matteo Poggi
We introduce a novel framework for training deep stereo networks effortlessly and without any ground-truth.
no code implementations • 16 Mar 2023 • Xin Qiao, Chenyang Ge, Youmin Zhang, Yanhui Zhou, Fabio Tosi, Matteo Poggi, Stefano Mattoccia
We propose a novel multi-stage depth super-resolution network, which progressively reconstructs high-resolution depth maps from explicit and implicit high-frequency features.
no code implementations • 19 Jan 2023 • Pierluigi Zama Ramirez, Alex Costanzino, Fabio Tosi, Matteo Poggi, Samuele Salti, Stefano Mattoccia, Luigi Di Stefano
Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization.
1 code implementation • 21 Dec 2022 • Jongbeom Baek, Gyeongnyeon Kim, Seonghoon Park, Honggyu An, Matteo Poggi, Seungryong Kim
We propose MaskingDepth, a novel semi-supervised learning framework for monocular depth estimation to mitigate the reliance on large ground-truth depth quantities.
1 code implementation • 1 Dec 2022 • Andrea Conti, Matteo Poggi, Stefano Mattoccia
We present a novel depth completion approach agnostic to the sparsity of depth points, that is very likely to vary in many practical applications.
1 code implementation • 24 Nov 2022 • Youmin Zhang, Matteo Poggi, Stefano Mattoccia
We present TemporalStereo, a coarse-to-fine stereo matching network that is highly efficient, and able to effectively exploit the past geometry and context information to boost matching accuracy.
no code implementations • 24 Nov 2022 • Luca De Luigi, Damiano Bolognini, Federico Domeniconi, Daniele De Gregorio, Matteo Poggi, Luigi Di Stefano
In this paper, we propose the first-ever real benchmark thought for evaluating Neural Radiance Fields (NeRFs) and, in general, Neural Rendering (NR) frameworks.
1 code implementation • 22 Nov 2022 • Jaime Spencer, C. Stella Qian, Chris Russell, Simon Hadfield, Erich Graf, Wendy Adams, Andrew J. Schofield, James Elder, Richard Bowden, Heng Cong, Stefano Mattoccia, Matteo Poggi, Zeeshan Khan Suri, Yang Tang, Fabio Tosi, Hao Wang, Youmin Zhang, Yusheng Zhang, Chaoqiang Zhao
This challenge evaluated the progress of self-supervised monocular depth estimation on the challenging SYNS-Patches dataset.
1 code implementation • 20 Oct 2022 • Matteo Poggi, Andrea Conti, Stefano Mattoccia
This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition.
1 code implementation • 6 Oct 2022 • Andrea Conti, Matteo Poggi, Filippo Aleotti, Stefano Mattoccia
Depth perception is pivotal in many fields, such as robotics and autonomous driving, to name a few.
no code implementations • 1 Sep 2022 • Matteo Poggi, Pierluigi Zama Ramirez, Fabio Tosi, Samuele Salti, Stefano Mattoccia, Luigi Di Stefano
We propose X-NeRF, a novel method to learn a Cross-Spectral scene representation given images captured from cameras with different light spectrum sensitivity, based on the Neural Radiance Fields formulation.
1 code implementation • 6 Aug 2022 • Chaoqiang Zhao, Youmin Zhang, Matteo Poggi, Fabio Tosi, Xianda Guo, Zheng Zhu, Guan Huang, Yang Tang, Stefano Mattoccia
Self-supervised monocular depth estimation is an attractive solution that does not require hard-to-source depth labels for training.
Ranked #1 on
Monocular Depth Estimation
on KITTI
1 code implementation • 21 Jul 2022 • Theodoros Panagiotakopoulos, Pier Luigi Dovesi, Linus Härenstam-Nielsen, Matteo Poggi
Unsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data and is, in most cases, carried out in offline manner.
no code implementations • CVPR 2022 • Fabio Tosi, Pierluigi Zama Ramirez, Matteo Poggi, Samuele Salti, Stefano Mattoccia, Luigi Di Stefano
We address the problem of registering synchronized color (RGB) and multi-spectral (MS) images featuring very different resolution by solving stereo matching correspondences.
no code implementations • CVPR 2022 • Pierluigi Zama Ramirez, Fabio Tosi, Matteo Poggi, Samuele Salti, Stefano Mattoccia, Luigi Di Stefano
We present a novel high-resolution and challenging stereo dataset framing indoor scenes annotated with dense and accurate ground-truth disparities.
no code implementations • 4 Apr 2022 • Alessio Mingozzi, Andrea Conti, Filippo Aleotti, Matteo Poggi, Stefano Mattoccia
In this paper, we aim to address this task leveraging a single RGB frame without additional depth sensors.
1 code implementation • 28 Oct 2021 • Filippo Aleotti, Fabio Tosi, Pierluigi Zama Ramirez, Matteo Poggi, Samuele Salti, Stefano Mattoccia, Luigi Di Stefano
We introduce a novel architecture for neural disparity refinement aimed at facilitating deployment of 3D computer vision on cheap and widespread consumer devices, such as mobile phones.
1 code implementation • ICCV 2021 • Matteo Poggi, Filippo Aleotti, Stefano Mattoccia
This paper proposes a framework to guide an optical flow network with external cues to achieve superior accuracy either on known or unseen domains.
1 code implementation • CVPR 2021 • Filippo Aleotti, Matteo Poggi, Stefano Mattoccia
This paper deals with the scarcity of data for training optical flow networks, highlighting the limitations of existing sources such as labeled synthetic datasets or unlabeled real videos.
1 code implementation • 2 Jan 2021 • Matteo Poggi, Seungryong Kim, Fabio Tosi, Sunok Kim, Filippo Aleotti, Dongbo Min, Kwanghoon Sohn, Stefano Mattoccia
Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, synchronized and rectified images.
1 code implementation • 14 Oct 2020 • Changjiang Cai, Matteo Poggi, Stefano Mattoccia, Philippos Mordohai
End-to-end deep networks represent the state of the art for stereo matching.
1 code implementation • ECCV 2020 • Filippo Aleotti, Fabio Tosi, Li Zhang, Matteo Poggi, Stefano Mattoccia
In many fields, self-supervised learning solutions are rapidly evolving and filling the gap with supervised approaches.
1 code implementation • ECCV 2020 • Matteo Poggi, Filippo Aleotti, Fabio Tosi, Giulio Zaccaroni, Stefano Mattoccia
Estimating the confidence of disparity maps inferred by a stereo algorithm has become a very relevant task in the years, due to the increasing number of applications leveraging such cue.
1 code implementation • 10 Jul 2020 • Matteo Poggi, Alessio Tonioni, Fabio Tosi, Stefano Mattoccia, Luigi Di Stefano
Thus, our network architecture and adaptation algorithms realize the first real-time self-adaptive deep stereo system and pave the way for a new paradigm that can facilitate practical deployment of end-to-end architectures for dense disparity regression.
1 code implementation • 10 Jun 2020 • Filippo Aleotti, Giulio Zaccaroni, Luca Bartolomei, Matteo Poggi, Fabio Tosi, Stefano Mattoccia
Depth perception is paramount to tackle real-world problems, ranging from autonomous driving to consumer applications.
1 code implementation • CVPR 2020 • Matteo Poggi, Filippo Aleotti, Fabio Tosi, Stefano Mattoccia
Self-supervised paradigms for monocular depth estimation are very appealing since they do not require ground truth annotations at all.
no code implementations • 18 Apr 2020 • Matteo Poggi, Fabio Tosi, Konstantinos Batsos, Philippos Mordohai, Stefano Mattoccia
Stereo matching is one of the longest-standing problems in computer vision with close to 40 years of studies and research.
1 code implementation • CVPR 2020 • Fabio Tosi, Filippo Aleotti, Pierluigi Zama Ramirez, Matteo Poggi, Samuele Salti, Luigi Di Stefano, Stefano Mattoccia
Whole understanding of the surroundings is paramount to autonomous systems.
1 code implementation • 22 Nov 2019 • Filippo Aleotti, Matteo Poggi, Fabio Tosi, Stefano Mattoccia
Scene flow is a challenging task aimed at jointly estimating the 3D structure and motion of the sensed environment.
no code implementations • 1 Oct 2019 • Pier Luigi Dovesi, Matteo Poggi, Lorenzo Andraghetti, Miquel Martí, Hedvig Kjellström, Alessandro Pieropan, Stefano Mattoccia
Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields.
1 code implementation • 9 Sep 2019 • Alessio Tonioni, Matteo Poggi, Stefano Mattoccia, Luigi Di Stefano
Extensive experimental results based on standard datasets and evaluation protocols prove that our technique can address effectively the domain shift issue with both stereo and monocular depth prediction architectures and outperforms other state-of-the-art unsupervised loss functions that may be alternatively deployed to pursue domain adaptation.
no code implementations • 8 Aug 2019 • Lorenzo Andraghetti, Panteleimon Myriokefalitakis, Pier Luigi Dovesi, Belen Luque, Matteo Poggi, Alessandro Pieropan, Stefano Mattoccia
Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras.
Ranked #47 on
Monocular Depth Estimation
on KITTI Eigen split
1 code implementation • CVPR 2019 • Matteo Poggi, Davide Pallotti, Fabio Tosi, Stefano Mattoccia
Our formulation is general and fully differentiable, thus enabling to exploit the additional sparse inputs in pre-trained deep stereo networks as well as for training a new instance from scratch.
1 code implementation • CVPR 2019 • Fabio Tosi, Filippo Aleotti, Matteo Poggi, Stefano Mattoccia
Depth estimation from a single image represents a fascinating, yet challenging problem with countless applications.
Ranked #51 on
Monocular Depth Estimation
on KITTI Eigen split
1 code implementation • CVPR 2019 • Alessio Tonioni, Fabio Tosi, Matteo Poggi, Stefano Mattoccia, Luigi Di Stefano
Deep convolutional neural networks trained end-to-end are the state-of-the-art methods to regress dense disparity maps from stereo pairs.
1 code implementation • 9 Oct 2018 • Pierluigi Zama Ramirez, Matteo Poggi, Fabio Tosi, Stefano Mattoccia, Luigi Di Stefano
For unsupervised training of these models, geometry has been effectively exploited by suitable images warping losses computed from views acquired by a stereo rig or a moving camera.
1 code implementation • ECCV 2018 • Fabio Tosi, Matteo Poggi, Antonio Benincasa, Stefano Mattoccia
Confidence measures for stereo gained popularity in recent years due to their improved capability to detect outliers and the increasing number of applications exploiting these cues.
1 code implementation • 5 Aug 2018 • Matteo Poggi, Fabio Tosi, Stefano Mattoccia
Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing.
Ranked #67 on
Monocular Depth Estimation
on KITTI Eigen split
4 code implementations • 29 Jun 2018 • Matteo Poggi, Filippo Aleotti, Fabio Tosi, Stefano Mattoccia
To tackle this issue, in this paper we propose a novel architecture capable to quickly infer an accurate depth map on a CPU, even of an embedded system, using a pyramid of features extracted from a single input image.
1 code implementation • ICCV 2017 • Alessio Tonioni, Matteo Poggi, Stefano Mattoccia, Luigi Di Stefano
Recent ground-breaking works have shown that deep neural networks can be trained end-to-end to regress dense disparity maps directly from image pairs.
no code implementations • ICCV 2017 • Matteo Poggi, Fabio Tosi, Stefano Mattoccia
However, since then major breakthroughs happened in this field: the availability of much larger and challenging datasets, novel and more effective stereo algorithms including ones based on deep-learning and confidence measures leveraging on machine learning techniques.
no code implementations • CVPR 2017 • Matteo Poggi, Stefano Mattoccia
Confidence measures estimate unreliable disparity assignments performed by a stereo matching algorithm and, as recently proved, can be used for several purposes.