Zobrazeno 1 - 10
of 277
pro vyhledávání: '"Park, Jaesik"'
Publikováno v:
IEEE Robotics & Automation Letters, 2023
We present an accurate and GPU-accelerated Stereo Visual SLAM design called Jetson-SLAM. It exhibits frame-processing rates above 60FPS on NVIDIA's low-powered 10W Jetson-NX embedded computer and above 200FPS on desktop-grade 200W GPUs, even in stere
Externí odkaz:
http://arxiv.org/abs/2410.04090
Autor:
Kumar, Ashish, Park, Jaesik
In the era of vision Transformers, the recent success of VanillaNet shows the huge potential of simple and concise convolutional neural networks (ConvNets). Where such models mainly focus on runtime, it is also crucial to simultaneously focus on othe
Externí odkaz:
http://arxiv.org/abs/2410.04089
Autor:
Kumar, Ashish, Park, Jaesik
Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decoding (CRED) mechanism that allows
Externí odkaz:
http://arxiv.org/abs/2410.04088
In this paper, we present a learning-based framework for sparse depth video completion. Given a sparse depth map and a color image at a certain viewpoint, our approach makes a cost volume that is constructed on depth hypothesis planes. To effectively
Externí odkaz:
http://arxiv.org/abs/2409.14935
Autor:
Lim, Hyungtae, Kim, Daebeom, Shin, Gunhee, Shi, Jingnan, Vizzo, Ignacio, Myung, Hyun, Park, Jaesik, Carlone, Luca
While global point cloud registration systems have advanced significantly in all aspects, many studies have focused on specific components, such as feature extraction, graph-theoretic pruning, or pose solvers. In this paper, we take a holistic view o
Externí odkaz:
http://arxiv.org/abs/2409.15615
Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately r
Externí odkaz:
http://arxiv.org/abs/2409.08857
Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- a
Externí odkaz:
http://arxiv.org/abs/2407.10542
The large abundance of perspective camera datasets facilitated the emergence of novel learning-based strategies for various tasks, such as camera localization, single image depth estimation, or view synthesis. However, panoramic or omnidirectional im
Externí odkaz:
http://arxiv.org/abs/2406.18898
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Channel pruning approaches for convolutional neural networks (ConvNets) deactivate the channels, statically or dynamically, and require special implementation. In addition, channel squeezing in representative ConvNets is carried out via 1x1 convoluti
Externí odkaz:
http://arxiv.org/abs/2406.10935
Autor:
Kang, Minguk, Zhang, Richard, Barnes, Connelly, Paris, Sylvain, Kwak, Suha, Park, Jaesik, Shechtman, Eli, Zhu, Jun-Yan, Park, Taesung
We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion distillation as a paired image
Externí odkaz:
http://arxiv.org/abs/2405.05967