Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Shen, Qiuhong"'
3D Gaussian splatting (3DGS), known for its groundbreaking performance and efficiency, has become a dominant 3D representation and brought progress to many 3D vision tasks. However, in this work, we reveal a significant security vulnerability that ha
Externí odkaz:
http://arxiv.org/abs/2410.08190
We embark on the age-old quest: unveiling the hidden dimensions of objects from mere glimpses of their visible parts. To address this, we present Vista3D, a framework that realizes swift and consistent 3D generation within a mere 5 minutes. At the he
Externí odkaz:
http://arxiv.org/abs/2409.12193
This study addresses the challenge of accurately segmenting 3D Gaussian Splatting from 2D masks. Conventional methods often rely on iterative gradient descent to assign each Gaussian a unique label, leading to lengthy optimization and sub-optimal sol
Externí odkaz:
http://arxiv.org/abs/2409.08270
Autor:
Yi, Xuanyu, Wu, Zike, Shen, Qiuhong, Xu, Qingshan, Zhou, Pan, Lim, Joo-Hwee, Yan, Shuicheng, Wang, Xinchao, Zhang, Hanwang
Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D representa
Externí odkaz:
http://arxiv.org/abs/2406.06367
Reconstructing 4D scenes from video inputs is a crucial yet challenging task. Conventional methods usually rely on the assumptions of multi-view video inputs, known camera parameters, or static scenes, all of which are typically absent under in-the-w
Externí odkaz:
http://arxiv.org/abs/2405.18426
User-friendly 3D object editing is a challenging task that has attracted significant attention recently. The limitations of direct 3D object editing without 2D prior knowledge have prompted increased attention towards utilizing 2D generative models f
Externí odkaz:
http://arxiv.org/abs/2405.05800
Autor:
Shen, Qiuhong, Wu, Zike, Yi, Xuanyu, Zhou, Pan, Zhang, Hanwang, Yan, Shuicheng, Wang, Xinchao
We tackle the challenge of efficiently reconstructing a 3D asset from a single image at millisecond speed. Existing methods for single-image 3D reconstruction are primarily based on Score Distillation Sampling (SDS) with Neural 3D representations. De
Externí odkaz:
http://arxiv.org/abs/2403.18795
3D reconstruction from a single-RGB image in unconstrained real-world scenarios presents numerous challenges due to the inherent diversity and complexity of objects and environments. In this paper, we introduce Anything-3D, a methodical framework tha
Externí odkaz:
http://arxiv.org/abs/2304.10261
Visual object tracking acts as a pivotal component in various emerging video applications. Despite the numerous developments in visual tracking, existing deep trackers are still likely to fail when tracking against objects with dramatic variation. Th
Externí odkaz:
http://arxiv.org/abs/2204.01513
Autor:
Shen, Qiuhong, Qiao, Lei, Guo, Jinyang, Li, Peixia, Li, Xin, Li, Bo, Feng, Weitao, Gan, Weihao, Wu, Wei, Ouyang, Wanli
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable to track ob
Externí odkaz:
http://arxiv.org/abs/2204.01475