Zobrazeno 1 - 10
of 184
pro vyhledávání: '"Lensch, Hendrik P. A."'
Autor:
Dihlmann, Jan-Niklas, Majumdar, Arjun, Engelhardt, Andreas, Braun, Raphael, Lensch, Hendrik P. A.
3D reconstruction and relighting of objects made from scattering materials present a significant challenge due to the complex light transport beneath the surface. 3D Gaussian Splatting introduced high-quality novel view synthesis at real-time speeds.
Externí odkaz:
http://arxiv.org/abs/2408.12282
Autor:
Doll, Simon, Hanselmann, Niklas, Schneider, Lukas, Schulz, Richard, Cordts, Marius, Enzweiler, Markus, Lensch, Hendrik P. A.
State-of-the-art approaches for autonomous driving integrate multiple sub-tasks of the overall driving task into a single pipeline that can be trained in an end-to-end fashion by passing latent representations between the different modules. In contra
Externí odkaz:
http://arxiv.org/abs/2406.06264
Autor:
Pleli, Alina, Baeuerle, Simon, Janus, Michel, Barth, Jonas, Mikut, Ralf, Lensch, Hendrik P. A.
Unsupervised clustering of wafer map defect patterns is challenging because the appearance of certain defect patterns varies significantly. This includes changing shape, location, density, and rotation of the defect area on the wafer. We present a ha
Externí odkaz:
http://arxiv.org/abs/2404.15436
Retinal fundus images play a crucial role in the early detection of eye diseases and, using deep learning approaches, recent studies have even demonstrated their potential for detecting cardiovascular risk factors and neurological disorders. However,
Externí odkaz:
http://arxiv.org/abs/2402.19186
Autor:
Engelhardt, Andreas, Raj, Amit, Boss, Mark, Zhang, Yunzhi, Kar, Abhishek, Li, Yuanzhen, Sun, Deqing, Brualla, Ricardo Martin, Barron, Jonathan T., Lensch, Hendrik P. A., Jampani, Varun
We present SHINOBI, an end-to-end framework for the reconstruction of shape, material, and illumination from object images captured with varying lighting, pose, and background. Inverse rendering of an object based on unconstrained image collections i
Externí odkaz:
http://arxiv.org/abs/2401.10171
Advances in image diffusion models have recently led to notable improvements in the generation of high-quality images. In combination with Neural Radiance Fields (NeRFs), they enabled new opportunities in 3D generation. However, most generative 3D ap
Externí odkaz:
http://arxiv.org/abs/2401.01647
Converting a model's internals to text can yield human-understandable insights about the model. Inspired by the recent success of training-free approaches for image captioning, we propose ZS-A2T, a zero-shot framework that translates the transformer
Externí odkaz:
http://arxiv.org/abs/2311.05043
Figurative and non-literal expressions are profoundly integrated in human communication. Visualising such expressions allow us to convey our creative thoughts, and evoke nuanced emotions. Recent text-to-image models like Stable Diffusion, on the othe
Externí odkaz:
http://arxiv.org/abs/2310.10543
Autor:
Holdenried-Krafft, Simon, Somers, Peter, Montes-Majarro, Ivonne A., Silimon, Diana, Tarín, Cristina, Fend, Falko, Lensch, Hendrik P. A.
Whole slide image (WSI) assessment is a challenging and crucial step in cancer diagnosis and treatment planning. WSIs require high magnifications to facilitate sub-cellular analysis. Precise annotations for patch- or even pixel-level classifications
Externí odkaz:
http://arxiv.org/abs/2307.07482
Autor:
Doll, Simon, Hanselmann, Niklas, Schneider, Lukas, Schulz, Richard, Enzweiler, Markus, Lensch, Hendrik P. A.
Publikováno v:
IEEE Robotics and Automation Letters, Vol. 9, No. 2 (2024), PP 1326-1333
Following the tracking-by-attention paradigm, this paper introduces an object-centric, transformer-based framework for tracking in 3D. Traditional model-based tracking approaches incorporate the geometric effect of object- and ego motion between fram
Externí odkaz:
http://arxiv.org/abs/2306.17602