Zobrazeno 1 - 10
of 84
pro vyhledávání: '"LIU Buyu"'
This work aims to address the multi-view perspective RGB generation from text prompts given Bird-Eye-View(BEV) semantics. Unlike prior methods that neglect layout consistency, lack the ability to handle detailed text prompts, or are incapable of gene
Externí odkaz:
http://arxiv.org/abs/2407.19468
Photorealistic simulation plays a crucial role in applications such as autonomous driving, where advances in neural radiance fields (NeRFs) may allow better scalability through the automatic creation of digital 3D assets. However, reconstruction qual
Externí odkaz:
http://arxiv.org/abs/2405.00900
Autor:
Min, Zhixiang, Zhuang, Bingbing, Schulter, Samuel, Liu, Buyu, Dunn, Enrique, Chandraker, Manmohan
Monocular 3D object localization in driving scenes is a crucial task, but challenging due to its ill-posed nature. Estimating 3D coordinates for each pixel on the object surface holds great potential as it provides dense 2D-3D geometric constraints f
Externí odkaz:
http://arxiv.org/abs/2305.17763
Influences of preparation process on the properties of high amylose corn starch-stearic acid complex
Publikováno v:
Shipin yu jixie, Vol 40, Iss 6, Pp 25-33 (2024)
[Objective] This study aimed to establish a preparation process for starch-lipid complex with high resistant starch （RS） content and to explore the effects of process parameters on the anti-digestibility of the complex. [Methods] Using RS content
Externí odkaz:
https://doaj.org/article/2d931bfa02584cbba29c626f97543a50
Adversarial attacks aim to perturb images such that a predictor outputs incorrect results. Due to the limited research in structured attacks, imposing consistency checks on natural multi-object scenes is a promising yet practical defense against conv
Externí odkaz:
http://arxiv.org/abs/2302.14166
Autor:
Shin, Inkyu, Tsai, Yi-Hsuan, Zhuang, Bingbing, Schulter, Samuel, Liu, Buyu, Garg, Sparsh, Kweon, In So, Yoon, Kuk-Jin
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for 3D semanti
Externí odkaz:
http://arxiv.org/abs/2204.12667
We propose a novel method on refining cross-person gaze prediction task with eye/face images only by explicitly modelling the person-specific differences. Specifically, we first assume that we can obtain some initial gaze prediction results with exis
Externí odkaz:
http://arxiv.org/abs/2106.14183
Trajectory prediction is a safety-critical tool for autonomous vehicles to plan and execute actions. Our work addresses two key challenges in trajectory prediction, learning multimodal outputs, and better predictions by imposing constraints using dri
Externí odkaz:
http://arxiv.org/abs/2104.08277
We propose an end-to-end network that takes a single perspective RGB image of a complex road scene as input, to produce occlusion-reasoned layouts in perspective space as well as a parametric bird's-eye-view (BEV) space. In contrast to prior works th
Externí odkaz:
http://arxiv.org/abs/2104.06730
Face anti-spoofing (FAS) seeks to discriminate genuine faces from fake ones arising from any type of spoofing attack. Due to the wide varieties of attacks, it is implausible to obtain training data that spans all attack types. We propose to leverage
Externí odkaz:
http://arxiv.org/abs/2011.14054