Third Workshop for Learning 3D with Multi-View Supervision
Real-time Gaussian Splatting with Progressive Block-based 3D Reconstruction-
[pdf]
[bibtex]@InProceedings{Khorramshahi_2026_CVPR, author = {Khorramshahi, Pirazh and Mahbub, Upal and Arora, Mehul and Nallabolu, Adithya Reddy and Dane, Gokce}, title = {Real-time Gaussian Splatting with Progressive Block-based 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {229-238} }
SplatTree: Voxel-Based Multi-Resolution Decoding for Feed-Forward 3D Gaussian Generation-
[pdf]
[bibtex]@InProceedings{Gong_2026_CVPR, author = {Gong, Ran and Ren, Zhehong and Fan, Tingyu and Hu, Yueyu and Wang, Yao}, title = {SplatTree: Voxel-Based Multi-Resolution Decoding for Feed-Forward 3D Gaussian Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {210-218} }
Indoor Asset Detection in Large Scale 360deg Drone-Captured Imagery via 3D Gaussian Splatting-
[pdf]
[bibtex]@InProceedings{Tang_2026_CVPR, author = {Tang, Monica and Zakhor, Avideh}, title = {Indoor Asset Detection in Large Scale 360deg Drone-Captured Imagery via 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {320-329} }
In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting-
[pdf]
[arXiv]
[bibtex]@InProceedings{Xiao_2026_CVPR, author = {Xiao, Wenhui and Goan, Ethan and Cruz, Rodrigo Santa and Ahmedt-Aristizabal, David and Salvado, Olivier and Fookes, Clinton and Lebrat, Leo}, title = {In Depth We Trust: Reliable Monocular Depth Supervision for Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {360-369} }
F3G-Avatar : Face Focussed Full-body Gaussian Avatar-
[pdf]
[bibtex]@InProceedings{Menu_2026_CVPR, author = {Menu, Willem and Akdag, Erkut and Quesado, Pedro and Kashefbahrami, Yasaman and Bondarev, Egor}, title = {F3G-Avatar : Face Focussed Full-body Gaussian Avatar}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {248-257} }
Coordinate-Reshaped Triplane Video Representation for Dynamic Gaussian Splatting Compression-
[pdf]
[bibtex]@InProceedings{Lee_2026_CVPR, author = {Lee, Dae Yeol and Kathariya, Birendra and Huang, Tsung-Wei and Su, Guan-Ming and Yin, Peng}, title = {Coordinate-Reshaped Triplane Video Representation for Dynamic Gaussian Splatting Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {239-247} }
LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Quesado_2026_CVPR, author = {Quesado, Pedro and Akdag, Erkut and Kashefbahrami, Yasaman and Menu, Willem and Bondarev, Egor}, title = {LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {279-288} }
TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K-
[pdf]
[bibtex]@InProceedings{D'Urso_2026_CVPR, author = {D'Urso, Mattia and Hu, Yuxi and Sormann, Christian and Rossi, Mattia and Fraundorfer, Friedrich}, title = {TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {200-209} }
PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Recasens_2026_CVPR, author = {Recasens, David and Maier, Robert and Civera, Javier and Tung, Tony and Boyer, Edmond}, title = {PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {289-299} }
SymmFusion: Injecting Multi-View-Consistent Generative Priors into Symmetry-Guided Point Cloud Completion-
[pdf]
[supp]
[bibtex]@InProceedings{Paregi_2026_CVPR, author = {Paregi, Bhanu Pratap and Kumar, Vaibhav}, title = {SymmFusion: Injecting Multi-View-Consistent Generative Priors into Symmetry-Guided Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {269-278} }
Surf-NeRF: Surface Regularised Neural Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Naylor_2026_CVPR, author = {Naylor, Jack and Ila, Viorela and Dansereau, Donald G.}, title = {Surf-NeRF: Surface Regularised Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {258-268} }
DanceNet3D: A 3D Dance Dataset with Multi-View Videos and 3DGS Reconstructions-
[pdf]
[bibtex]@InProceedings{Wei_2026_CVPR, author = {Wei, Shihang and Li, Mingjian and Gong, Ran and Hu, Yueyu and Wang, Yao}, title = {DanceNet3D: A 3D Dance Dataset with Multi-View Videos and 3DGS Reconstructions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {350-359} }
PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tran_2026_CVPR, author = {Tran, Anh Thuan and Kosecka, Jana}, title = {PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {330-339} }
Reducing Closeup Frequency Artifacts for Level-of-Detail 3D Gaussian Splatting-
[pdf]
[bibtex]@InProceedings{Zhou_2026_CVPR, author = {Zhou, Leonardo and Mao, Dayou and Lin, Yuchen and Ebadi, Ashkan and Wong, Alexander and Chen, Yuhao}, title = {Reducing Closeup Frequency Artifacts for Level-of-Detail 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {370-378} }
SDFoam: Signed-Distance Foam for explicit surface reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rech_2026_CVPR, author = {Rech, Antonella and Conci, Nicola and Garau, Nicola}, title = {SDFoam: Signed-Distance Foam for explicit surface reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {300-308} }
Towards Minimal Focal Stack in Shape from Focus-
[pdf]
[arXiv]
[bibtex]@InProceedings{Ashfaq_2026_CVPR, author = {Ashfaq, Khurram and Mahmood, Muhammad Tariq}, title = {Towards Minimal Focal Stack in Shape from Focus}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {190-199} }
Leveraging Mamba and Attention for Robust Multi-View Pedestrian Tracking-
[pdf]
[bibtex]@InProceedings{Alturki_2026_CVPR, author = {Alturki, Reef and Sardari, Faegheh and Hilton, Adrian and Guillemaut, Jean-Yves}, title = {Leveraging Mamba and Attention for Robust Multi-View Pedestrian Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {180-189} }
Benchmarking Stereo Geometry Estimation in the Wild-
[pdf]
[supp]
[bibtex]@InProceedings{Tan_2026_CVPR, author = {Tan, Jeff and Keetha, Nikhil and Liu, Yifei and Tulsiani, Shubham and Ramanan, Deva}, title = {Benchmarking Stereo Geometry Estimation in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {309-319} }
Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting-
[pdf]
[arXiv]
[bibtex]@InProceedings{Hsu_2026_CVPR, author = {Hsu, Tsuheng and Liu, Guiyu and Kannala, Juho and Heikkil\"a, Janne}, title = {Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {219-228} }
NGOcc: Normal-Guided 3D Occupancy Prediction with Observability-aware Time Fusion-
[pdf]
[bibtex]@InProceedings{Wang_2026_CVPR, author = {Wang, Jufei and Wei, Mingwei and Qiu, Tianheng and Wei, Hu and Ni, Huasheng and Huang, Xuan}, title = {NGOcc: Normal-Guided 3D Occupancy Prediction with Observability-aware Time Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {340-349} }
CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Abualhanud_2026_CVPR, author = {Abualhanud, Samer and Grannemann, Christian and Mehltretter, Max}, title = {CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {169-179} }

