Zobrazeno 1 - 10
of 118
pro vyhledávání: '"SANDER, PEDRO V."'
Autor:
Wang, Sheng, Tian, Yao, Mei, Xiaodong, Sun, Ge, Cheng, Jie, Ma, Fulong, Sander, Pedro V., Liang, Junwei
Decision-making and planning in autonomous driving critically reflect the safety of the system, making effective planning imperative. Current imitation learning-based planning algorithms often merge historical trajectories with present observations t
Externí odkaz:
http://arxiv.org/abs/2411.17253
Looping videos are short video clips that can be looped endlessly without visible seams or artifacts. They provide a very attractive way to capture the dynamism of natural scenes. Existing methods have been mostly limited to 2D representations. In th
Externí odkaz:
http://arxiv.org/abs/2303.05312
We propose an approach to simulate and render realistic water animation from a single still input photograph. We first segment the water surface, estimate rendering parameters, and compute water reflection textures with a combination of neural networ
Externí odkaz:
http://arxiv.org/abs/2210.02553
Neural Radiance Field (NeRF) has gained considerable attention recently for 3D scene reconstruction and novel view synthesis due to its remarkable synthesis quality. However, image blurriness caused by defocus or motion, which often occurs when captu
Externí odkaz:
http://arxiv.org/abs/2111.14292
In this paper, we propose an image compression algorithm called Microshift. We employ an algorithm hardware co-design methodology, yielding a hardware-friendly compression approach with low power consumption. In our method, the image is first micro-s
Externí odkaz:
http://arxiv.org/abs/2104.09820
Contaminants such as dust, dirt and moisture adhering to the camera lens can greatly affect the quality and clarity of the resulting image or video. In this paper, we propose a video restoration method to automatically remove these contaminants and p
Externí odkaz:
http://arxiv.org/abs/2104.08852
We propose a novel framework to produce cartoon videos by fetching the color information from two input keyframes while following the animated motion guided by a user sketch. The key idea of the proposed approach is to estimate the dense cross-domain
Externí odkaz:
http://arxiv.org/abs/2008.04149
We propose a novel learning method to rectify document images with various distortion types from a single input image. As opposed to previous learning-based methods, our approach seeks to first learn the distortion flow on input image patches rather
Externí odkaz:
http://arxiv.org/abs/1909.09470
We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion dataset to
Externí odkaz:
http://arxiv.org/abs/1909.03459
This paper presents the first end-to-end network for exemplar-based video colorization. The main challenge is to achieve temporal consistency while remaining faithful to the reference style. To address this issue, we introduce a recurrent framework t
Externí odkaz:
http://arxiv.org/abs/1906.09909