Zobrazeno 1 - 10
of 1 368
pro vyhledávání: '"Kämäräinen A"'
Video deblurring aims at recovering sharp details from a sequence of blurry frames. Despite the proliferation of depth sensors in mobile phones and the potential of depth information to guide deblurring, depth-aware deblurring has received only limit
Externí odkaz:
http://arxiv.org/abs/2409.01274
Autor:
Wang, Vivienne Huiling, Wang, Tinghuai, Yang, Wenyan, Kämäräinen, Joni-Kristian, Pajarinen, Joni
In goal-conditioned hierarchical reinforcement learning (HRL), a high-level policy specifies a subgoal for the low-level policy to reach. Effective HRL hinges on a suitable subgoal represen tation function, abstracting state space into latent subgoal
Externí odkaz:
http://arxiv.org/abs/2406.16707
Recent results suggest that splitting topological navigation into robot-independent and robot-specific components improves navigation performance by enabling the robot-independent part to be trained with data collected by robots of different types. H
Externí odkaz:
http://arxiv.org/abs/2309.17260
Publikováno v:
Communications Earth & Environment, Vol 5, Iss 1, Pp 1-8 (2024)
Abstract It is widely acknowledged that the intensity, frequency and duration of heatwaves are increasing worldwide, including the Arctic. However, less attention has been paid to the land area affected by heatwaves. Here, using atmospheric reanalysi
Externí odkaz:
https://doaj.org/article/cff42213280441d4be09035e9a739cb8
Camera motion introduces spatially varying blur due to the depth changes in the 3D world. This work investigates scene configurations where such blur is produced under parallax camera motion. We present a simple, yet accurate, Image Compositing Blur
Externí odkaz:
http://arxiv.org/abs/2303.09334
Autor:
Yang, Wenyan, Angleraud, Alexandre, Pieters, Roel S., Pajarinen, Joni, Kämäräinen, Joni-Kristian
Robot control for tactile feedback-based manipulation can be difficult due to the modeling of physical contacts, partial observability of the environment, and noise in perception and control. This work focuses on solving partial observability of cont
Externí odkaz:
http://arxiv.org/abs/2303.02646
Offline goal-conditioned reinforcement learning (GCRL) can be challenging due to overfitting to the given dataset. To generalize agents' skills outside the given dataset, we propose a goal-swapping procedure that generates additional trajectories. To
Externí odkaz:
http://arxiv.org/abs/2302.08865
In goal-conditioned offline reinforcement learning, an agent learns from previously collected data to go to an arbitrary goal. Since the offline data only contains a finite number of trajectories, a main challenge is how to generate more data. Goal-s
Externí odkaz:
http://arxiv.org/abs/2302.07741
Publikováno v:
Natural Hazards and Earth System Sciences, Vol 24, Pp 1835-1842 (2024)
In this article we present a method for numerical simulations of extreme sea levels using synthetic low-pressure systems as atmospheric forcing. Our simulations can be considered to be estimates of the high sea levels that may be reached when a low-p
Externí odkaz:
https://doaj.org/article/f9158e073fea443ba221bab10d9547ac
Autor:
Siekkinen, Matti, Kämäräinen, Teemu
Depth maps are needed by various graphics rendering and processing operations. Depth map streaming is often necessary when such operations are performed in a distributed system and it requires in most cases fast performing compression, which is why v
Externí odkaz:
http://arxiv.org/abs/2206.15183