Zobrazeno 1 - 10
of 166
pro vyhledávání: '"Zhai, Guangyao"'
Autor:
Zhai, Guangyao, Örnek, Evin Pınar, Chen, Dave Zhenyu, Liao, Ruotong, Di, Yan, Navab, Nassir, Tombari, Federico, Busam, Benjamin
We present EchoScene, an interactive and controllable generative model that generates 3D indoor scenes on scene graphs. EchoScene leverages a dual-branch diffusion model that dynamically adapts to scene graphs. Existing methods struggle to handle sce
Externí odkaz:
http://arxiv.org/abs/2405.00915
During the Gaussian Splatting optimization process, the scene's geometry can gradually deteriorate if its structure is not deliberately preserved, especially in non-textured regions such as walls, ceilings, and furniture surfaces. This degradation si
Externí odkaz:
http://arxiv.org/abs/2403.11324
Autor:
Chen, Yamei, Di, Yan, Zhai, Guangyao, Manhardt, Fabian, Zhang, Chenyangguang, Zhang, Ruida, Tombari, Federico, Navab, Nassir, Busam, Benjamin
Category-level object pose estimation, aiming to predict the 6D pose and 3D size of objects from known categories, typically struggles with large intra-class shape variation. Existing works utilizing mean shapes often fall short of capturing this var
Externí odkaz:
http://arxiv.org/abs/2311.11125
Autor:
Di, Yan, Zhang, Chenyangguang, Wang, Chaowei, Zhang, Ruida, Zhai, Guangyao, Li, Yanyan, Fu, Bowen, Ji, Xiangyang, Gao, Shan
In this paper, we present ShapeMatcher, a unified self-supervised learning framework for joint shape canonicalization, segmentation, retrieval and deformation. Given a partially-observed object in an arbitrary pose, we first canonicalize the object b
Externí odkaz:
http://arxiv.org/abs/2311.11106
Autor:
Zhai, Guangyao, Cai, Xiaoni, Huang, Dianye, Di, Yan, Manhardt, Fabian, Tombari, Federico, Navab, Nassir, Busam, Benjamin
Object rearrangement is pivotal in robotic-environment interactions, representing a significant capability in embodied AI. In this paper, we present SG-Bot, a novel rearrangement framework that utilizes a coarse-to-fine scheme with a scene graph as t
Externí odkaz:
http://arxiv.org/abs/2309.12188
Autor:
Zhang, Chenyangguang, Di, Yan, Zhang, Ruida, Zhai, Guangyao, Manhardt, Fabian, Tombari, Federico, Ji, Xiangyang
Reconstructing hand-held objects from a single RGB image is an important and challenging problem. Existing works utilizing Signed Distance Fields (SDF) reveal limitations in comprehensively capturing the complex hand-object interactions, since SDF is
Externí odkaz:
http://arxiv.org/abs/2308.08231
Autor:
Di, Yan, Zhang, Chenyangguang, Wang, Pengyuan, Zhai, Guangyao, Zhang, Ruida, Manhardt, Fabian, Busam, Benjamin, Ji, Xiangyang, Tombari, Federico
In this paper, we present a novel shape reconstruction method leveraging diffusion model to generate 3D sparse point cloud for the object captured in a single RGB image. Recent methods typically leverage global embedding or local projection-based fea
Externí odkaz:
http://arxiv.org/abs/2308.07837
Autor:
Zhai, Guangyao, Örnek, Evin Pınar, Wu, Shun-Cheng, Di, Yan, Tombari, Federico, Navab, Nassir, Busam, Benjamin
Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing me
Externí odkaz:
http://arxiv.org/abs/2305.16283
Autor:
Jung, HyunJun, Ruhkamp, Patrick, Zhai, Guangyao, Brasch, Nikolas, Li, Yitong, Verdie, Yannick, Song, Jifei, Zhou, Yiren, Armagan, Anil, Ilic, Slobodan, Leonardis, Ales, Navab, Nassir, Busam, Benjamin
Learning-based methods to solve dense 3D vision problems typically train on 3D sensor data. The respectively used principle of measuring distances provides advantages and drawbacks. These are typically not compared nor discussed in the literature due
Externí odkaz:
http://arxiv.org/abs/2303.14840
Autor:
Zhu, Dekai, Zhai, Guangyao, Di, Yan, Manhardt, Fabian, Berkemeyer, Hendrik, Tran, Tuan, Navab, Nassir, Tombari, Federico, Busam, Benjamin
Reliable multi-agent trajectory prediction is crucial for the safe planning and control of autonomous systems. Compared with single-agent cases, the major challenge in simultaneously processing multiple agents lies in modeling complex social interact
Externí odkaz:
http://arxiv.org/abs/2303.00575