Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Song, Jifei"'
Autor:
Jung, HyunJun, Li, Weihang, Wu, Shun-Cheng, Bittner, William, Brasch, Nikolas, Song, Jifei, Pérez-Pellitero, Eduardo, Zhang, Zhensong, Moreau, Arthur, Navab, Nassir, Busam, Benjamin
Traditionally, 3d indoor datasets have generally prioritized scale over ground-truth accuracy in order to obtain improved generalization. However, using these datasets to evaluate dense geometry tasks, such as depth rendering, can be problematic as t
Externí odkaz:
http://arxiv.org/abs/2410.22715
Autor:
Li, Gen, Tsagkas, Nikolaos, Song, Jifei, Mon-Williams, Ruaridh, Vijayakumar, Sethu, Shao, Kun, Sevilla-Lara, Laura
Affordance, defined as the potential actions that an object offers, is crucial for robotic manipulation tasks. A deep understanding of affordance can lead to more intelligent AI systems. For example, such knowledge directs an agent to grasp a knife b
Externí odkaz:
http://arxiv.org/abs/2408.10123
Autor:
Ververas, Evangelos, Potamias, Rolandos Alexandros, Song, Jifei, Deng, Jiankang, Zafeiriou, Stefanos
Following the advent of NeRFs, 3D Gaussian Splatting (3D-GS) has paved the way to real-time neural rendering overcoming the computational burden of volumetric methods. Following the pioneering work of 3D-GS, several methods have attempted to achieve
Externí odkaz:
http://arxiv.org/abs/2404.19149
Autor:
Zhang, Zhongqun, Song, Jifei, Pérez-Pellitero, Eduardo, Zhou, Yiren, Chang, Hyung Jin, Leonardis, Aleš
Modeling hand-object interactions is a fundamentally challenging task in 3D computer vision. Despite remarkable progress that has been achieved in this field, existing methods still fail to synthesize the hand-object interaction photo-realistically,
Externí odkaz:
http://arxiv.org/abs/2402.05532
Autor:
Jung, HyunJun, Brasch, Nikolas, Song, Jifei, Perez-Pellitero, Eduardo, Zhou, Yiren, Li, Zhihao, Navab, Nassir, Busam, Benjamin
Recent advances in neural radiance fields enable novel view synthesis of photo-realistic images in dynamic settings, which can be applied to scenarios with human animation. Commonly used implicit backbones to establish accurate models, however, requi
Externí odkaz:
http://arxiv.org/abs/2312.15059
Autor:
Shaw, Richard, Nazarczuk, Michal, Song, Jifei, Moreau, Arthur, Catley-Chandar, Sibi, Dhamo, Helisa, Perez-Pellitero, Eduardo
Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling interacti
Externí odkaz:
http://arxiv.org/abs/2312.13308
Recent advancements in 3D avatar generation excel with multi-view supervision for photorealistic models. However, monocular counterparts lag in quality despite broader applicability. We propose ReCaLaB to close this gap. ReCaLaB is a fully-differenti
Externí odkaz:
http://arxiv.org/abs/2312.04784
Autor:
Dhamo, Helisa, Nie, Yinyu, Moreau, Arthur, Song, Jifei, Shaw, Richard, Zhou, Yiren, Pérez-Pellitero, Eduardo
3D head animation has seen major quality and runtime improvements over the last few years, particularly empowered by the advances in differentiable rendering and neural radiance fields. Real-time rendering is a highly desirable goal for real-world ap
Externí odkaz:
http://arxiv.org/abs/2312.02902
Autor:
Moreau, Arthur, Song, Jifei, Dhamo, Helisa, Shaw, Richard, Zhou, Yiren, Pérez-Pellitero, Eduardo
This work addresses the problem of real-time rendering of photorealistic human body avatars learned from multi-view videos. While the classical approaches to model and render virtual humans generally use a textured mesh, recent research has developed
Externí odkaz:
http://arxiv.org/abs/2311.17113
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