Zobrazeno 1 - 10
of 214
pro vyhledávání: '"ROSU, Radu"'
Publikováno v:
24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), pp. 173-180, 2022. IEEE
Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire original dataset
Externí odkaz:
http://arxiv.org/abs/2403.17130
Autor:
Esser, Felix, Rosu, Radu Alexandru, Cornelißen, André, Klingbeil, Lasse, Kuhlmann, Heiner, Behnke, Sven
With the need to feed a growing world population, the efficiency of crop production is of paramount importance. To support breeding and field management, various characteristics of the plant phenotype need to be measured -- a time-consuming process w
Externí odkaz:
http://arxiv.org/abs/2310.11516
Autor:
Rosu, Radu Alexandru, Behnke, Sven
Neural radiance-density field methods have become increasingly popular for the task of novel-view rendering. Their recent extension to hash-based positional encoding ensures fast training and inference with visually pleasing results. However, density
Externí odkaz:
http://arxiv.org/abs/2211.12562
We present Neural Strands, a novel learning framework for modeling accurate hair geometry and appearance from multi-view image inputs. The learned hair model can be rendered in real-time from any viewpoint with high-fidelity view-dependent effects. O
Externí odkaz:
http://arxiv.org/abs/2207.14067
Semantic segmentation is a core ability required by autonomous agents, as being able to distinguish which parts of the scene belong to which object class is crucial for navigation and interaction with the environment. Approaches which use only one ti
Externí odkaz:
http://arxiv.org/abs/2203.15469
Autor:
Beul, Marius, Schwarz, Max, Quenzel, Jan, Splietker, Malte, Bultmann, Simon, Schleich, Daniel, Rochow, Andre, Pavlichenko, Dmytro, Rosu, Radu Alexandru, Lowin, Patrick, Scheider, Bruno, Schreiber, Michael, Süberkrüb, Finn, Behnke, Sven
The Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2020 posed diverse challenges for unmanned aerial vehicles (UAVs). We present our four tailored UAVs, specifically developed for individual aerial-robot tasks of MBZIRC, including custom
Externí odkaz:
http://arxiv.org/abs/2201.03844
Autor:
Asatryan, Babken, Baskar, Shankar, Berne, Paola, Blommaert, Dominique, Dormal, Fabien, Boccellino, Antonio, Ciconte, Giuseppe, Giustetto, Carla, Haqqani, Harris, Jackson, Liang J., DG, Latcu, Lellouche, Nicolas, Marai, Ibrahim, Nakahara, Shiro, Pannone, Luigi, de Asmundis, Carlo, Pavri, Behzad B., Porretta, Alessandra Pia, Pruvot, Etienne, Rosu, Radu, Scherr, Daniel, Steinfurt, Johannes, Yagishita, Atsuhiko, Belhassen, Bernard, Conte, Giulio, Steinberg, Christian, Whitaker, John, Khan, Habib R., Laredo, Mikael, Doldi, Florian, Ho, Reginald, Tadros, Rafik, Dinov, Boris, Chorin, Ehud, Hansom, Simon, Waintraub, Xavier, Eckardt, Lars, Jankelson, Lior, Peichl, Petr, Mellor, Greg, Sy, Raymond W., Rattanawong, Pattara, Stojkovic, Stefan, Garber, Leonid, Suna, Gonca, Kautzner, Josef, Chan, Kim Hoe, Srivathsan, Komandoor, Tedrow, Usha, Havranek, Stepan, Murgatroyd, Francis, Shauer, Ayelet, Winkel, Bo Gregers, Page, Stephen P., Milman, Anat, Lador, Adi, Ayou, Romeo, Sellal, Jean Marc, Chevalier, Philippe, García-Fernández, F. Javier, Reichlin, Tobias, Shah, Dipen, Nazer, Babak, Bermudez-Jimenez, Francisco, Nagase, Satoshi, Morita, Hiroshi, Nam, Gi-Byoung, Pappone, Carlo, Lambiase, Pier D., Strohmer, Bernhard, Stuehlinger, Markus, Gandjbakhch, Estelle, Schulze-Bahr, Eric, Krahn, Andrew D., Tovia-Brodie, Oholi
Publikováno v:
In JACC: Clinical Electrophysiology August 2024 10(8):1794-1809
Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. Applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of structured da
Externí odkaz:
http://arxiv.org/abs/2108.03917
Autor:
Rosu, Radu Alexandru, Behnke, Sven
Multi-View Stereo (MVS) is a core task in 3D computer vision. With the surge of novel deep learning methods, learned MVS has surpassed the accuracy of classical approaches, but still relies on building a memory intensive dense cost volume. Novel View
Externí odkaz:
http://arxiv.org/abs/2108.03880
Autor:
Rosu, Radu Alexandru, Behnke, Sven
Modern rendering libraries provide unprecedented realism, producing real-time photorealistic 3D graphics on commodity hardware. Visual fidelity, however, comes at the cost of increased complexity and difficulty of usage, with many rendering parameter
Externí odkaz:
http://arxiv.org/abs/2012.03325