Source code and datasets

 

Source code, datasets and trained models for the following papers:

  1. -L. Bartolomei, M. Poggi, A. Conti, S. Mattoccia, “LiDAR-Event Stereo Fusion with Hallucinations”, European Conference on Computer Vision (ECCV 2024), Milano, Italy, Sep 29th - Oct 4th, 2024 [Arxiv | PDF | Code]

  2. -A. Conti, M. Poggi,, V. Cambareri, S. Mattoccia, “Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensor”, European Conference on Computer Vision (ECCV 2024), Milano, ItalySep 29th - Oct 4th, 2024 [Arxiv | PDF | Code]

  3. -R. Fan, M. Poggi, S. Mattoccia, “Exploring Few-Beam LiDAR Assistance in Self-Supervised Multi-Frame Depth Estimation”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024), October 14-18, 2024, Abu Dhabi, UAE [PDF | Code]

  4. -L. Bartolomei, M. Poggi, F. Tosi, A. Conti, S. Mattoccia, “Stereo-Depth Fusion through Virtual Pattern Projection”, [PDF | Project | Code]

  5. -L. Bartolomei, M. Poggi, A. Conti, F. Tosi, S. Mattoccia, “Revisiting depth completion from a stereo matching perspective for cross-domain generalization”, International Conference on 3D Vision 2024 (3DV 2024), Davos, Switzerland, March 18-21, 2024 [PDF | Supplementary | Arxiv | Video | Project | Code]

  6. -A. Conti, M. Poggi, V. Cambareri, S. Mattoccia, “Range-agnostic multi-view depth estimation with keyframe selection”, International Conference on 3D Vision 2024 (3DV 2024), Davos, Switzerland, March 18-21, 2024 [PDF | Supplementary | Arxiv | Video | Project | Code]

  7. -H. Li, M. Poggi, F. Tosi, S. Mattoccia, “On-Site Adaptation for Monocular Depth Estimation with a Static Camera”, oral presentation at The 34th British Machine Vision Conference (BMVC2023), Aberdeen, UK, 20th - 24th November 2023 [PDF | Code]

  8. -R. Fan, F. Tosi, M. Poggi, S. Mattoccia, “Lightweight Self-Supervised Depth Estimation with few-beams LiDAR Data”, The 34th British Machine Vision Conference (BMVC2023), Aberdeen, UK, 20th - 24th November 2023 [PDF | Code]

  9. -L. Bartolomei, M. Poggi, F. Tosi, A. Conti, S. Mattoccia, “Active Stereo Without Pattern Projector”, IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, October 4-6, 2023 [PDF | Supplementary | Arxiv | Project | Code]

  10. -Y. Zhang, F. Tosi, S. Mattoccia, M. Poggi, “GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction”, IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, October 4-6, 2023 [PDF | Supplementary | Arxiv | Project | Code]

  11. -C. Zhao, M. Poggi, F. Tosi, l. Zhou, Q. Sun, Y. Tang,  S. Mattoccia, “GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes”, IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, October 4-6, 2023 [PDF | Supplementary | Arxiv | Video | Code]

  12. -A. Costanzino, P. Zama Ramirez, M. Poggi, F. Tosi, S. Mattoccia, L. Di Stefano, “Learning Depth Estimation for Transparent and Mirror Surfaces”, IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, October 4-6, 2023 [PDF | Supplementary | Arxiv | Video | Code]

  13. -Y. Zhang, M. Poggi, S. Mattoccia, “TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023), Detroit, Michigan USA, October 1-5, 2023 [PDF | Supplementary] | Video | Arxiv | Code]

  14. -Y. Zhang, X. Guo, M. Poggi, Z. Zhu, G. Huang, S. Mattoccia, “CompletionFormer: Depth Completion with Convolutions and Vision Transformers”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, June 18-22, 2023 [PDF | Supplementary | Arxiv | Code]

  15. -A. Conti, M. Poggi, S. Mattoccia, “Sparsity Agnostic Depth Completion”, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), Waikoloa, Hawaii (USA), January 3–7, 2023 [PDF | Project]

  16. -A. Conti, M. Poggi, F. Aleotti, S. Mattoccia, “Unsupervised confidence for LiDAR depth maps and applications”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Kyoto, Japan, October 23–27, 2022 [PDF | Video | Code]

  17. -M. Poggi, A. Conti, S. Mattoccia, “Multi-view Guided Multi-view Stereo”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), Kyoto, Japan, October 23–27, 2022 [PDF | Video | Code]

  18. -C. Zhao, Y. Zhang, M. Poggi, F. Tosi, X. Guo, Z. Zhu, G. Huang, Y. Tang, S. Mattoccia, “MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer”, International Conference on 3D Vision (3DV2022), Prague, Czechia, September 12-15, 2022 [PDF | Video | Code]

  19. -M. Poggi, P. Zama Ramirez, F. Tosi, S. Salti, S. Mattoccia, L. Di Stefano, “Cross-Spectral Neural Radiance Fields”, International Conference on 3D Vision (3DV2022), Prague, Czechia, September 12-15, 2022 [PDF | Project |  Dataset]

  20. -P. Zama Ramirez*, F. Tosi*, M. Poggi*, S. Salti, S. Mattoccia, L. Di Stefano, “Open challenges in deep stereo: the Booster dataset”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, USA, June 19-24, 2022 [PDF | Supplementary | Project page | Dataset | Video]

  21. -F. Tosi*, P. Zama Ramirez*, M. Poggi*, S. Salti, S. Mattoccia, L. Di Stefano, “RGB-Multispectral matching: dataset, learning methodology, evaluation”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, USA, June 19-24, 2022 [PDF | Supplementary | Project page | Dataset | Video]

  22. -F. Aleotti, F. Tosi, P. Zama Ramirez, M. Poggi, S. Salti, S. Mattoccia, L. Di Stefano, “Neural disparity refinement for arbitrary resolution stereo”, oral presentation at International Conference on 3D Vision (3DV 2021), virtual, December 1-3, 2021 [PDF | Code] - BEST PAPER AWARD HONORABLE MENTION

  23. -M. Poggi, F. Aleotti, S. Mattoccia, “Sensor-guided optical flow”, International Conference on Computer Vision (ICCV 2021), virtual, October 11-17, 2021 [PDF | Supplementary | Code | Video]

  24. -F. Aleotti, M. Poggi, S. Mattoccia, “Learning optical flow from still images”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2021), virtual, June 19-25, 2021 [PDF | Supplementary | Code | Video]

  25. -M. Poggi, A. Tonioni, F. Tosi, S. Mattoccia, L. Di Stefano, “Continual adaptation for deep stereo”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 [PDF | PDF(Pre-print) | Video | Code]

  26. -C. Cai, M. Poggi, S. Mattoccia, P. Mordohai, “Matching-space Stereo Networks for Cross-domain Generalization”, 8th International Virtual Conference on 3D Vision (3DV 2020), November 25-28, 2020, virtually in Fukuoka, Japan [PDF | Code]

  27. -F. Aleotti, F. Tosi, L. Zhang, M. Poggi, S. Mattoccia, “Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation”, 16th European Conference on Computer Vision (ECCV 2020), 23-28 August 2020, Glasgow, UK [PDF | Video | Code]

  28. -M. Poggi, F. Aleotti, F. Tosi, G. Zaccaroni, S. Mattoccia, “Self-adapting confidence estimation for stereo”, 16th European Conference on Computer Vision (ECCV 2020), 23-28 August 2020, Glasgow, UK [PDF | Video | Code]

  29. -F. Aleotti, G. Zaccaroni, L. Bartolomei, M. Poggi, F. Tosi, S. Mattoccia, “Real-time single image depth perception in the wild with handheld devices”, Sensors 2021, 21(1), 15; [PDF | Video_1 | Video_2 | Video_3 | Demo | Code]



  30. -M. Poggi, F. Aleotti, F. Tosi, S. Mattoccia, "On the uncertainty of self-supervised monocular depth estimation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), June 16-18, 2020, Seattle, Washington, USA [PDF | Code | Video | Supp]






  31. -F. Tosi, F. Aleotti, P. Zama Ramirez, M. Poggi, S. Salti, L. Di Stefano, S. Mattoccia, "Distilled semantics for comprehensive scene understanding from videos", IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), June 16-18, 2020, Seattle, Washington, USA [PDF | Code | Supp] 


  32. -F. Aleotti, M. Poggi, F. Tosi, S. Mattoccia, “Learning end-to-end scene flow by distilling single tasks knowledge”, Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), New York, USA, February 7-12 2020 [PDF | Video | Code | Project]


  33. -A. Tonioni, M. Poggi, S. Mattoccia, L. Di Stefano, “Unsupervised domain adaptation for depth prediction from images”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 42(10), pp 2396 - 2409, October 1, 2020, 10.1109/TPAMI.2019.2940948, [PDF | PDF(Pre-print) | Video | Code]


  34. - M. Poggi, D. Pallotti, F. Tosi, S. Mattoccia, “Guided stereo matching”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, USA, June 16-20 2019 [PDF | Code | Video]


  35. -F. Tosi, F. Aleotti, M. Poggi, S. Mattoccia, "Learning monocular depth estimation infusing traditional stereo knowledge", IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, USA, June 16-20 2019 [PDF | Supplementary | Code | Video | Project]

      
  36. -A. Tonioni, F. Tosi, M. Poggi, S. Mattoccia, L. Di Stefano, "Real-time self-adaptive deep stereo", oral presentation at IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, USA, June 16-20 2019 [PDF | Supplementary | Code | Video]


  37. -P. Zama Ramirez, M. Poggi, F. Tosi, S. Mattoccia, L. Di Stefano, "Geometry meets semantic for semi-supervised monocular depth estimation", 14th Asian Conference on Computer Vision (ACCV 2018), December 2-6, 2018, Perth, Australia [PDF | Code | Video]

     

  38. -F. Tosi, M. Poggi, A. Benincasa, S. Mattoccia, “Beyond local reasoning for stereo confidence estimation with deep learning”, 15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, September 8-14, 2018 [PDF | Bibtex | Code]


  39. -M. Poggi, F. Tosi, S. Mattoccia, "Learning monocular depth estimation with unsupervised trinocular assumptions", 6th international conference on 3D Vision (3DV 2018), September 5-8, 2018, Verona, Italy [PDF | Video | Bibtex | Supplementary | Code]


    - M. Poggi, F. Aleotti, F. Tosi, S. Mattoccia, “Towards real-time unsupervised monocular depth estimation on CPU”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018), Madrid, Spain, October, 1-5, 2018 [PDF | Bibtex | Video | Code]

  40. -M. Poggi, F. Tosi, S. Mattoccia, “Quantitative evaluation of confidence measures in a machine learning world”, spotlight presentation at International Conference on Computer Vision (ICCV 2017), October 22-29, 2017, Venice, Italy [PDF | Supplementary | Code]


- A. Tonioni, M. Poggi, S. Mattoccia, L. Di Stefano, “Unsupervised adaptation for deep stereo”, International Conference on Computer Vision (ICCV 2017), October 22-29, 2017, Venice, Italy [PDF | Supplementary | Code]


- F. Tosi, M. Poggi, A. Tonioni, L. Di Stefano, S. Mattoccia, “Learning confidence measures in the wild”, 28th British Machine Vision Conference (BMVC 2017), September 4-7, 2017, Imperial College London, UK [PDF| Bibtex | Code]


- M. Poggi, S. Mattoccia, “Leveraging confident points for accurate depth refinement on embedded systems”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, Hawaii (USA), July 21-26, 2017 [PDF | Code]


- M. Poggi, S. Mattoccia, “Learning a general-purpose confidence measure based on O(1) features and a smarter aggregation strategy for semi global matching”, oral presentation at the 2016 International Conference on 3D Vision (3DV 2016), October 25-28, 2016, Stanford University, California, USA [PDF]


- M. Poggi, S. Mattoccia, “Deep Stereo Fusion: combining multiple disparity hypotheses with deep-learning”, 2016 International Conference on 3D Vision (3DV 2016), October 25-28, 2016, Stanford University, California, USA [PDF]


  1. -M. Poggi, S. Mattoccia, “Learning from scratch a confidence measure”, 27th British Machine Vision Conference (BMVC 2016), September 19-22, 2016, York, UK [PDF | Code]


  2. - S. Mattoccia, S. Giardino, A. Gambini, "Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering", Asian Conference on Computer Vision (ACCV2009), September 23-27, 2009,  Xi'an, China[Pdf | Bibtex | Additional experimental results | Binary: software | Source: Code]


  3. -Smart camera with OV7670 sensors and Zynq, [Video_1, Video_2, Video_3, Code]







    The previous design has been ported to PYNQ Z2 by Mattia Mazzoli and Matteo Di Lorenzi (link to their project available in Github)
  4. -Optical Tracking Velocimetry (OTV): code available here

    F. Tosi, M. Rocca, F. Aleotti, M. Poggi, S. Mattoccia, F. Tauro, E. Toth, S. Grimaldi, “Enabling image-based streamflow monitoring at the edge”, Remote Sensing, 2020, 12(12), 2047, https://doi.org/10.3390/rs12122047 [PDF]

    F. Tauro, F. Tosi, S. Mattoccia, E. Toth, R. Piscopia, S. Grimaldi, "Optical Tracking Velocimetry (OTV): leveraging optical flow and trajectory-based filtering for surface streamflow observations", Remote Sensing, 2018, 10(12), 2010 [PDF | Video]

  5. -

  6. -
    Acknowledgments

We gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan X and a Titan XP GPU