Zobrazeno 1 - 10
of 688
pro vyhledávání: '"KIM HANSUNG"'
Semantic Scene Completion (SSC) is a critical task in computer vision, that utilized in applications such as virtual reality (VR). SSC aims to construct detailed 3D models from partial views by transforming a single 2D image into a 3D representation,
Externí odkaz:
http://arxiv.org/abs/2412.01431
We introduce an Implicit Game-Theoretic MPC (IGT-MPC), a decentralized algorithm for two-agent motion planning that uses a learned value function that predicts the game-theoretic interaction outcomes as the terminal cost-to-go function in a model pre
Externí odkaz:
http://arxiv.org/abs/2411.13983
Modern GPUs incorporate specialized matrix units such as Tensor Cores to accelerate GEMM operations central to deep learning workloads. However, existing matrix unit designs are tightly coupled to the SIMT core, limiting the size and energy efficienc
Externí odkaz:
http://arxiv.org/abs/2408.12073
Current human pose estimation systems focus on retrieving an accurate 3D global estimate of a single person. Therefore, this paper presents one of the first 3D multi-person human pose estimation systems that is able to work in real-time and is also a
Externí odkaz:
http://arxiv.org/abs/2403.09437
We propose a hierarchical architecture designed for scalable real-time Model Predictive Control (MPC) in complex, multi-modal traffic scenarios. This architecture comprises two key components: 1) RAID-Net, a novel attention-based Recurrent Neural Net
Externí odkaz:
http://arxiv.org/abs/2402.01116
Depth estimation from a single image is a challenging problem in computer vision because binocular disparity or motion information is absent. Whereas impressive performances have been reported in this area recently using end-to-end trained deep neura
Externí odkaz:
http://arxiv.org/abs/2311.10042
Autor:
Hardy, Peter, Kim, Hansung
Current unsupervised 2D-3D human pose estimation (HPE) methods do not work in multi-person scenarios due to perspective ambiguity in monocular images. Therefore, we present one of the first studies investigating the feasibility of unsupervised multi-
Externí odkaz:
http://arxiv.org/abs/2309.14865
Autor:
Hardy, Peter, Kim, Hansung
We present LInKs, a novel unsupervised learning method to recover 3D human poses from 2D kinematic skeletons obtained from a single image, even when occlusions are present. Our approach follows a unique two-step process, which involves first lifting
Externí odkaz:
http://arxiv.org/abs/2309.07243
Achieving accurate material segmentation for 3-channel RGB images is challenging due to the considerable variation in a material's appearance. Hyperspectral images, which are sets of spectral measurements sampled at multiple wavelengths, theoreticall
Externí odkaz:
http://arxiv.org/abs/2307.11466
DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches
The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation performance, their
Externí odkaz:
http://arxiv.org/abs/2305.03919