Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Li, ZiZhang"'
Autor:
Zhang, Yunzhi, Li, Zizhang, Raj, Amit, Engelhardt, Andreas, Li, Yuanzhen, Hou, Tingbo, Wu, Jiajun, Jampani, Varun
We propose 3D Congealing, a novel problem of 3D-aware alignment for 2D images capturing semantically similar objects. Given a collection of unlabeled Internet images, our goal is to associate the shared semantic parts from the inputs and aggregate th
Externí odkaz:
http://arxiv.org/abs/2404.02125
Autor:
Li, Zizhang, Litvak, Dor, Li, Ruining, Zhang, Yunzhi, Jakab, Tomas, Rupprecht, Christian, Wu, Shangzhe, Vedaldi, Andrea, Wu, Jiajun
Learning 3D models of all animals on the Earth requires massively scaling up existing solutions. With this ultimate goal in mind, we develop 3D-Fauna, an approach that learns a pan-category deformable 3D animal model for more than 100 animal species
Externí odkaz:
http://arxiv.org/abs/2401.02400
Autor:
Sargent, Kyle, Li, Zizhang, Shah, Tanmay, Herrmann, Charles, Yu, Hong-Xing, Zhang, Yunzhi, Chan, Eric Ryan, Lagun, Dmitry, Fei-Fei, Li, Sun, Deqing, Wu, Jiajun
We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced
Externí odkaz:
http://arxiv.org/abs/2310.17994
Implicit neural rendering, which uses signed distance function (SDF) representation with geometric priors (such as depth or surface normal), has led to impressive progress in the surface reconstruction of large-scale scenes. However, applying this me
Externí odkaz:
http://arxiv.org/abs/2303.09152
Recently, neural implicit surfaces have become popular for multi-view reconstruction. To facilitate practical applications like scene editing and manipulation, some works extend the framework with semantic masks input for the object-compositional rec
Externí odkaz:
http://arxiv.org/abs/2303.08605
Autor:
Xu, Kechun, Chen, Runjian, Zhao, Shuqi, Li, Zizhang, Yu, Hongxiang, Chen, Ci, Wang, Yue, Xiong, Rong
Self-assessment rules play an essential role in safe and effective real-world robotic applications, which verify the feasibility of the selected action before actual execution. But how to utilize the self-assessment results to re-choose actions remai
Externí odkaz:
http://arxiv.org/abs/2302.13024
Autor:
Xu, Kechun, Zhao, Shuqi, Zhou, Zhongxiang, Li, Zizhang, Pi, Huaijin, Zhu, Yifeng, Wang, Yue, Xiong, Rong
We focus on the task of language-conditioned grasping in clutter, in which a robot is supposed to grasp the target object based on a language instruction. Previous works separately conduct visual grounding to localize the target object, and generate
Externí odkaz:
http://arxiv.org/abs/2302.12610
Recently, the image-wise implicit neural representation of videos, NeRV, has gained popularity for its promising results and swift speed compared to regular pixel-wise implicit representations. However, the redundant parameters within the network str
Externí odkaz:
http://arxiv.org/abs/2207.08132
Loss functions play an important role in training deep-network-based object detectors. The most widely used evaluation metric for object detection is Average Precision (AP), which captures the performance of localization and classification sub-tasks
Externí odkaz:
http://arxiv.org/abs/2112.05138
Referring image segmentation is a typical multi-modal task, which aims at generating a binary mask for referent described in given language expressions. Prior arts adopt a bimodal solution, taking images and languages as two modalities within an enco
Externí odkaz:
http://arxiv.org/abs/2111.10747