Learning Generative 3D Scene Models for Training and Validating Intelligent Systems

Informazioni relative al progetto

LEGO-3D

ID dell’accordo di sovvenzione: 850533

DOI

10.3030/850533

Data della firma CE 22 Ottobre 2019

Data di avvio 1 Ottobre 2020

Data di completamento 31 Marzo 2026

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 467 500,00

Contributo UE

€ 1 467 500,00

Coordinato da

EBERHARD KARLS UNIVERSITAET TUEBINGEN
Germany

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Conference proceedings (27)

ARAH: Animatable Volume Rendering of Articulated Human SDFs

Autori: S. Wang, K. Schwarz, A. Geiger, S. Tang
Pubblicato in: European Conference on Computer Vision (ECCV), 2022
Editore: Springer

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

Autori: C. Reiser, S. Peng, Y. Liao, A. Geiger
Pubblicato in: International Conference on Computer Vision (ICCV), 2021
Editore: IEEE/CVF

AG3D: Learning to Generate 3D Avatars from 2D Image Collections

Autori: Zijian Dong, Xu Chen, Jinlong Yang, Michael J. Black, Otmar Hilliges, Andreas Geiger
Pubblicato in: 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2024, Pagina/e 14870-14881
Editore: IEEE
DOI: 10.1109/iccv51070.2023.01370

SMD-Nets: Stereo Mixture Density Networks

Autori: F. Tosi, Y. Liao, C. Schmitt, A. Geiger
Pubblicato in: Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Editore: IEEE/CV

Hidden Biases of End-to-End Driving Models

Autori: Bernhard Jaeger, Kashyap Chitta, Andreas Geiger
Pubblicato in: 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2024, Pagina/e 8206-8215
Editore: IEEE
DOI: 10.1109/iccv51070.2023.00757

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

Autori: Oechsle, Michael; Peng, Songyou; Geiger, Andreas
Pubblicato in: International Conference on Computer Vision (ICCV), 2021
Editore: IEEE/CVF
DOI: 10.1109/iccv48922.2021.00554

Shape As Points: A Differentiable Poisson Solver

Autori: "Peng, Songyou; Jiang, Chiyu ""Max""; Liao, Yiyi; Niemeyer, Michael; Pollefeys, Marc; Geiger, Andreas"
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2021
Editore: Curran Associates, Inc.
DOI: 10.48550/arxiv.2106.03452

IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing

Autori: Shaofei Wang, Božidar Antić, Andreas Geiger, Siyu Tang
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Pagina/e 1877-1888
Editore: IEEE
DOI: 10.1109/cvpr52733.2024.00184

MuRF: Multi-Baseline Radiance Fields

Autori: Haofei XU, Anpei Chen, Yuedong Chen, Christos Sakaridis, Yulun Zhang, Marc Pollefeys, Andreas Geiger, Fisher Yu
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Pagina/e 20041-20050
Editore: IEEE
DOI: 10.1109/cvpr52733.2024.01894

GOOD: Exploring geometric cues for detecting objects in an open world

Autori: H. Huang, A. Geiger, D. Zhang
Pubblicato in: International Conference on Learning Representations (ICLR), 2023
Editore: OpenReview

Mip-Splatting: Alias-Free 3D Gaussian Splatting

Autori: Zehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler, Andreas Geiger
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Pagina/e 19447-19456
Editore: IEEE
DOI: 10.1109/cvpr52733.2024.01839

2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Autori: Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, Shenghua Gao
Pubblicato in: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24, 2024, Pagina/e 1-11
Editore: ACM
DOI: 10.1145/3641519.3657428

GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields

Autori: Geiger, Andreas; Niemeyer, Michael
Pubblicato in: Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Editore: IEEE/CVF
DOI: 10.48550/arxiv.2011.12100

Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

Autori: Aditya Prakash, Kashyap Chitta, Andreas Geiger
Pubblicato in: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Pagina/e 7073-7083
Editore: IEEE
DOI: 10.1109/cvpr46437.2021.00700

NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis

Autori: Zinuo You, Andreas Geiger, Anpei Chen
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Pagina/e 19833-19843
Editore: IEEE
DOI: 10.1109/cvpr52733.2024.01875

Projected GANs Converge Faster

Autori: A. Sauer, K. Chitta, J. Müller, A. Geiger
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2021
Editore: Curran Associates, Inc.
DOI: 10.48550/arxiv.2111.01007

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

Autori: A. Sauer, K. Schwarz, A. Geiger
Pubblicato in: International Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), 2022
Editore: Association for Computing Machinery
DOI: 10.48550/arxiv.2202.00273

MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images

Autori: S. Wang, M. Mihajlovic, Q. Ma, A. Geiger, S. Tang
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2021
Editore: Curran Associates, Inc.

GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers

Autori: Takeru Miyato, Bernhard Jaeger, Max Welling, Andreas Geiger
Pubblicato in: International Conference on Learning Representations (ICLR), 2024
Editore: OpenReview.net
DOI: 10.48550/arxiv.2310.10375

VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

Autori: K. Schwarz, A. Sauer, M. Niemeyer, Y. Liao, A. Geiger
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2022
Editore: Curran Associates, Inc.

Parting with Misconceptions about Learning-based Vehicle Motion Planning

Autori: Dauner, Daniel; Hallgarten, Marcel; Geiger, Andreas; Chitta, Kashyap
Pubblicato in: Conference on Robot Learning, 2023
Editore: Proceedings of Machine Learning Research
DOI: 10.48550/arxiv.2306.07962

Counterfactual Generative Networks

Autori: Sauer, Axel; Geiger, Andreas
Pubblicato in: International Conference on Learning Representations (ICLR), 2021
Editore: OpenReview
DOI: 10.48550/arxiv.2101.06046

3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting

Autori: Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, Siyu Tang
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Pagina/e 5020-5030
Editore: IEEE
DOI: 10.1109/cvpr52733.2024.00480

CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields

Autori: Michael Niemeyer; Andreas Geiger
Pubblicato in: International Conference on 3D Vision (3DV), 2021
Editore: IEEE Computer Society
DOI: 10.1109/3dv53792.2021.00103

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting

Autori: Hongyu Zhou, Jiahao Shao, Lu Xu, Dongfeng Bai, Weichao Qiu, Bingbing Liu, Yue Wang, Andreas Geiger, Yiyi Liao
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Pagina/e 21336-21345
Editore: IEEE
DOI: 10.1109/cvpr52733.2024.02016

GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs

Autori: Gege Gao, Weiyang Liu, Anpei Chen, Andreas Geiger, Bernhard Schölkopf
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, Pagina/e 21295-21304
Editore: IEEE
DOI: 10.1109/cvpr52733.2024.02012

MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

Autori: Z. Yu, S. Peng, M. Niemeyer, T. Sattler, A. Geiger
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2022
Editore: Curran Associates, Inc.

Peer reviewed articles (8)

KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D

Autori: Liao, Yiyi; Xie, Jun; Geiger, Andreas
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 1, 2022, ISSN 1939-3539
Editore: IEEE Computer Society
DOI: 10.1109/tpami.2022.3179507

End-to-End Autonomous Driving: Challenges and Frontiers

Autori: Li Chen, Penghao Wu, Kashyap Chitta, Bernhard Jaeger, Andreas Geiger, Hongyang Li
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 46, 2024, Pagina/e 10164-10183, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2024.3435937

Unifying Flow, Stereo and Depth Estimation

Autori: Haofei Xu, Jing Zhang, Jianfei Cai, Hamid Rezatofighi, Fisher Yu, Dacheng Tao, Andreas Geiger
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 45, 2023, Pagina/e 13941-13958, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2023.3298645

Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis

Autori: Christian Reiser, Stephan Garbin, Pratul Srinivasan, Dor Verbin, Richard Szeliski, Ben Mildenhall, Jonathan Barron, Peter Hedman, Andreas Geiger
Pubblicato in: ACM Transactions on Graphics, Numero 43, 2024, Pagina/e 1-14, ISSN 0730-0301
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3658130

MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes

Autori: Christian Reiser, Rick Szeliski, Dor Verbin, Pratul Srinivasan, Ben Mildenhall, Andreas Geiger, Jon Barron, Peter Hedman
Pubblicato in: ACM Transactions on Graphics, Numero 42, 2024, Pagina/e 1-12, ISSN 0730-0301
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3592426

TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving

Autori: K. Chitta, A. Prakash, B. Jaeger, Z. Yu, K. Renz, A. Geiger
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2022.3200245

Towards Scalable Multi-View Reconstruction of Geometry and Materials

Autori: Carolin Schmitt, Božidar Antić, Andrei Neculai, Joo Ho Lee, Andreas Geiger
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numero 45, 2024, Pagina/e 15850-15869, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2023.3314348

Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes

Autori: Zehao Yu, Torsten Sattler, Andreas Geiger
Pubblicato in: ACM Transactions on Graphics, Numero 43, 2024, Pagina/e 1-13, ISSN 0730-0301
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3687937

Book chapters (3)

LaRa: Efficient Large-Baseline Radiance Fields

Autori: Anpei Chen, Haofei Xu, Stefano Esposito, Siyu Tang, Andreas Geiger
Pubblicato in: Lecture Notes in Computer Science, Computer Vision – ECCV 2024, 2024, Pagina/e 338-355
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-73247-8_20

Efficient Depth-Guided Urban View Synthesis

Autori: Sheng Miao, Jiaxin Huang, Dongfeng Bai, Weichao Qiu, Bingbing Liu, Andreas Geiger, Yiyi Liao
Pubblicato in: Lecture Notes in Computer Science, Computer Vision – ECCV 2024, 2025, Pagina/e 90-107
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-73404-5_6

SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic

Autori: Kashyap Chitta, Daniel Dauner, Andreas Geiger
Pubblicato in: Lecture Notes in Computer Science, Computer Vision – ECCV 2024, 2024, Pagina/e 57-74
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-73235-5_4