Zobrazeno 1 - 10
of 132
pro vyhledávání: '"Steinberger, Markus"'
Autor:
Mallick, Saswat Subhajyoti, Goel, Rahul, Kerbl, Bernhard, Carrasco, Francisco Vicente, Steinberger, Markus, De La Torre, Fernando
3D Gaussian Splatting (3DGS) has transformed novel-view synthesis with its fast, interpretable, and high-fidelity rendering. However, its resource requirements limit its usability. Especially on constrained devices, training performance degrades quic
Externí odkaz:
http://arxiv.org/abs/2406.15643
Autor:
Radl, Lukas, Steiner, Michael, Parger, Mathias, Weinrauch, Alexander, Kerbl, Bernhard, Steinberger, Markus
Gaussian Splatting has emerged as a prominent model for constructing 3D representations from images across diverse domains. However, the efficiency of the 3D Gaussian Splatting rendering pipeline relies on several simplifications. Notably, reducing G
Externí odkaz:
http://arxiv.org/abs/2402.00525
Due to the omnipresence of Neural Radiance Fields (NeRFs), the interest towards editable implicit 3D representations has surged over the last years. However, editing implicit or hybrid representations as used for NeRFs is difficult due to the entangl
Externí odkaz:
http://arxiv.org/abs/2312.09913
Modern Neural Radiance Fields (NeRFs) learn a mapping from position to volumetric density leveraging proposal network samplers. In contrast to the coarse-to-fine sampling approach with two NeRFs, this offers significant potential for acceleration usi
Externí odkaz:
http://arxiv.org/abs/2306.00696
Autor:
Parger, Mathias, Ertl, Alexander, Eibensteiner, Paul, Mueller, Joerg H., Winter, Martin, Steinberger, Markus
Training a sparse neural network from scratch requires optimizing connections at the same time as the weights themselves. Typically, the weights are redistributed after a predefined number of weight updates, removing a fraction of the parameters of e
Externí odkaz:
http://arxiv.org/abs/2210.14012
Autor:
Parger, Mathias, Tang, Chengcheng, Neff, Thomas, Twigg, Christopher D., Keskin, Cem, Wang, Robert, Steinberger, Markus
Convolutional neural network inference on video input is computationally expensive and requires high memory bandwidth. Recently, DeltaCNN managed to reduce the cost by only processing pixels with significant updates over the previous frame. However,
Externí odkaz:
http://arxiv.org/abs/2210.09887
Novel view synthesis has recently been revolutionized by learning neural radiance fields directly from sparse observations. However, rendering images with this new paradigm is slow due to the fact that an accurate quadrature of the volume rendering e
Externí odkaz:
http://arxiv.org/abs/2207.10312
Autor:
Parger, Mathias, Tang, Chengcheng, Twigg, Christopher D., Keskin, Cem, Wang, Robert, Steinberger, Markus
Convolutional neural network inference on video data requires powerful hardware for real-time processing. Given the inherent coherence across consecutive frames, large parts of a video typically change little. By skipping identical image regions and
Externí odkaz:
http://arxiv.org/abs/2203.03996
The humble loop shrinking property played a central role in the inception of modern topology but it has been eclipsed by more abstract algebraic formalism. This is particularly true in the context of detecting relevant non-contractible loops on surfa
Externí odkaz:
http://arxiv.org/abs/2105.13168
Autor:
Neff, Thomas, Stadlbauer, Pascal, Parger, Mathias, Kurz, Andreas, Mueller, Joerg H., Chaitanya, Chakravarty R. Alla, Kaplanyan, Anton, Steinberger, Markus
Publikováno v:
Computer Graphics Forum Volume 40, Issue 4, 2021
The recent research explosion around implicit neural representations, such as NeRF, shows that there is immense potential for implicitly storing high-quality scene and lighting information in compact neural networks. However, one major limitation pre
Externí odkaz:
http://arxiv.org/abs/2103.03231