Zobrazeno 1 - 10
of 193
pro vyhledávání: '"Diller, Christian"'
Autor:
Diller, Christian, Dai, Angela
We propose CG-HOI, the first method to address the task of generating dynamic 3D human-object interactions (HOIs) from text. We model the motion of both human and object in an interdependent fashion, as semantically rich human motion rarely happens i
Externí odkaz:
http://arxiv.org/abs/2311.16097
Autor:
Schütz, Moritz, Diller, Christian
Publikováno v:
Erdkunde, 2024 Jan 01. 78(1), 57-70.
Externí odkaz:
https://www.jstor.org/stable/27301042
We present a generative approach to forecast long-term future human behavior in 3D, requiring only weak supervision from readily available 2D human action data. This is a fundamental task enabling many downstream applications. The required ground-tru
Externí odkaz:
http://arxiv.org/abs/2211.14309
Autor:
Karic, Sarah, Diller, Christian
Publikováno v:
Erdkunde, 2023 Oct 01. 77(4), 287-302.
Externí odkaz:
https://www.jstor.org/stable/27273792
Publikováno v:
Erdkunde, 2023 Apr 01. 77(2), 113-126.
Externí odkaz:
https://www.jstor.org/stable/27225853
We propose the task of forecasting characteristic 3d poses: from a short sequence observation of a person, predict a future 3d pose of that person in a likely action-defining, characteristic pose -- for instance, from observing a person picking up an
Externí odkaz:
http://arxiv.org/abs/2011.15079
We present a novel approach that converts partial and noisy RGB-D scans into high-quality 3D scene reconstructions by inferring unobserved scene geometry. Our approach is fully self-supervised and can hence be trained solely on real-world, incomplete
Externí odkaz:
http://arxiv.org/abs/1912.00036
Autor:
Diller, Christian, Velte, Nadine
Publikováno v:
In Evaluation and Program Planning June 2023 98
Autor:
Diller, Christian1 christian.diller@geogr.uni-giessen.de
Publikováno v:
Raumforschung und Raumordnung. 2024, Vol. 82 Issue 2, p188-190. 3p.