Benjamin Ummenhofer

29 papers A* 8Journal 14Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
KernelFoundry: Hardware-aware evolutionary GPU kernel optimization.
CoRR
Nina Wiedemann, Quentin Leboutet, Michael Paulitsch, Diana Wofk, Benjamin Ummenhofer
2025 J jnl
HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video.
CoRR
Hongchi Xia, Chih-Hao Lin, Hao-Yu Hsu, Quentin Leboutet, Katelyn Gao, Michael Paulitsch, Benjamin Ummenhofer, Shenlong Wang
2025 J jnl
PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors.
CoRR
Yujin Chen, Yinyu Nie, Benjamin Ummenhofer, Reiner Birkl, Michael Paulitsch, Matthias Nießner
2025 J jnl
Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework.
CoRR
Nina Wiedemann, Sainan Liu, Quentin Leboutet, Katelyn Gao, Benjamin Ummenhofer, Michael Paulitsch, Kai Yuan
2025 J jnl
Unifi3D: A Study on 3D Representations for Generation and Reconstruction in a Common Framework.
Trans. Mach. Learn. Res.
Nina Wiedemann, Sainan Liu, Quentin Leboutet, Katelyn Gao, Benjamin Ummenhofer, Michael Paulitsch, Kai Yuan
2024 — conf
Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation.
ECCV (9)
Yujin Chen, Yinyu Nie, Benjamin Ummenhofer, Reiner Birkl, Michael Paulitsch, Matthias Müller, Matthias Nießner
2024 J jnl
Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation.
CoRR
Yujin Chen, Yinyu Nie, Benjamin Ummenhofer, Reiner Birkl, Michael Paulitsch, Matthias Müller, Matthias Nießner
2024 — conf
Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting.
3DV
Benjamin Ummenhofer, Sanskar Agrawal, Rene Sepúlveda, Yixing Lao, Kai Zhang, Tianhang Cheng, Stephan R. Richter, Shenlong Wang, Germán Ros
2024 J jnl
Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting.
CoRR
Benjamin Ummenhofer, Sanskar Agrawal, Rene Sepúlveda, Yixing Lao, Kai Zhang, Tianhang Cheng, Stephan R. Richter, Shenlong Wang, Germán Ros
2022 A* conf
Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics.
NeurIPS
Lukas Prantl, Benjamin Ummenhofer, Vladlen Koltun, Nils Thuerey
2022 J jnl
Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics.
CoRR
Lukas Prantl, Benjamin Ummenhofer, Vladlen Koltun, Nils Thuerey
2022 A* conf
Segment-Fusion: Hierarchical Context Fusion for Robust 3D Semantic Segmentation.
CVPR
Anirud Thyagharajan, Benjamin Ummenhofer, Prashant Laddha, Om Ji Omer, Sreenivas Subramoney
2021 A* conf
Adaptive Surface Reconstruction with Multiscale Convolutional Kernels.
ICCV
Benjamin Ummenhofer, Vladlen Koltun
2021 J jnl
Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusion.
CoRR
Anirud Thyagharajan, Benjamin Ummenhofer, Prashant Laddha, Om Ji Omer, Sreenivas Subramoney
2020 J jnl
DeepTAM: Deep Tracking and Mapping with Convolutional Neural Networks.
Int. J. Comput. Vis.
Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
2020 A* conf
Lagrangian Fluid Simulation with Continuous Convolutions.
ICLR
Benjamin Ummenhofer, Lukas Prantl, Nils Thuerey, Vladlen Koltun
2019 A* conf
CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth.
CVPR
José M. Fácil, Benjamin Ummenhofer, Huizhong Zhou, Luis Montesano, Thomas Brox, Javier Civera
2019 J jnl
CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth.
CoRR
José M. Fácil, Benjamin Ummenhofer, Huizhong Zhou, Luis Montesano, Thomas Brox, Javier Civera
2018 — conf
DeepTAM: Deep Tracking and Mapping.
ECCV (16)
Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
2018 J jnl
DeepTAM: Deep Tracking and Mapping.
CoRR
Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
2018 — —
Introduction to dense reconstruction from multiple images.
Benjamin Ummenhofer
2018 — conf
Temporally Consistent Depth Estimation in Videos with Recurrent Architectures.
ECCV Workshops (3)
Denis Tananaev, Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
2017 A* conf
DeMoN: Depth and Motion Network for Learning Monocular Stereo.
CVPR
Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig, Nikolaus Mayer, Eddy Ilg, Alexey Dosovitskiy, Thomas Brox
2017 J jnl
Global, Dense Multiscale Reconstruction for a Billion Points.
Int. J. Comput. Vis.
Benjamin Ummenhofer, Thomas Brox
2016 J jnl
DeMoN: Depth and Motion Network for Learning Monocular Stereo.
CoRR
Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig, Nikolaus Mayer, Eddy Ilg, Alexey Dosovitskiy, Thomas Brox
2015 A* conf
Global, Dense Multiscale Reconstruction for a Billion Points.
ICCV
Benjamin Ummenhofer, Thomas Brox
2013 A* conf
Point-Based 3D Reconstruction of Thin Objects.
ICCV
Benjamin Ummenhofer, Thomas Brox
2012 — conf
Dense 3D Reconstruction with a Hand-Held Camera.
DAGM/OAGM Symposium
Benjamin Ummenhofer, Thomas Brox
2011 — conf
Large Displacement Optical Flow for Volumetric Image Sequences.
DAGM-Symposium
Benjamin Ummenhofer