Zobrazeno 1 - 10
of 1 610
pro vyhledávání: '"ZENG, Gang"'
Autor:
Tang, Jiaxiang, Li, Zhaoshuo, Hao, Zekun, Liu, Xian, Zeng, Gang, Liu, Ming-Yu, Zhang, Qinsheng
Current auto-regressive mesh generation methods suffer from issues such as incompleteness, insufficient detail, and poor generalization. In this paper, we propose an Auto-regressive Auto-encoder (ArAE) model capable of generating high-quality 3D mesh
Externí odkaz:
http://arxiv.org/abs/2409.18114
Rendering novel view images in dynamic scenes is a crucial yet challenging task. Current methods mainly utilize NeRF-based methods to represent the static scene and an additional time-variant MLP to model scene deformations, resulting in relatively l
Externí odkaz:
http://arxiv.org/abs/2406.03697
Autor:
Wang, Qi, Lu, Ruijie, Xu, Xudong, Wang, Jingbo, Wang, Michael Yu, Dai, Bo, Zeng, Gang, Xu, Dan
The advancement of diffusion models has pushed the boundary of text-to-3D object generation. While it is straightforward to composite objects into a scene with reasonable geometry, it is nontrivial to texture such a scene perfectly due to style incon
Externí odkaz:
http://arxiv.org/abs/2406.02461
Text-to-texture synthesis has become a new frontier in 3D content creation thanks to the recent advances in text-to-image models. Existing methods primarily adopt a combination of pretrained depth-aware diffusion and inpainting models, yet they exhib
Externí odkaz:
http://arxiv.org/abs/2403.11878
3D content creation has achieved significant progress in terms of both quality and speed. Although current feed-forward models can produce 3D objects in seconds, their resolution is constrained by the intensive computation required during training. I
Externí odkaz:
http://arxiv.org/abs/2402.05054
4D content generation has achieved remarkable progress recently. However, existing methods suffer from long optimization times, a lack of motion controllability, and a low quality of details. In this paper, we introduce DreamGaussian4D (DG4D), an eff
Externí odkaz:
http://arxiv.org/abs/2312.17142
Autor:
Liu, Xian, Zhan, Xiaohang, Tang, Jiaxiang, Shan, Ying, Zeng, Gang, Lin, Dahua, Liu, Xihui, Liu, Ziwei
Realistic 3D human generation from text prompts is a desirable yet challenging task. Existing methods optimize 3D representations like mesh or neural fields via score distillation sampling (SDS), which suffers from inadequate fine details or excessiv
Externí odkaz:
http://arxiv.org/abs/2311.17061
Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their
Externí odkaz:
http://arxiv.org/abs/2309.16653
This paper investigates the potential of enhancing Neural Radiance Fields (NeRF) with semantics to expand their applications. Although NeRF has been proven useful in real-world applications like VR and digital creation, the lack of semantics hinders
Externí odkaz:
http://arxiv.org/abs/2305.16233
Autor:
Wang, Wenhai, Chen, Zhe, Chen, Xiaokang, Wu, Jiannan, Zhu, Xizhou, Zeng, Gang, Luo, Ping, Lu, Tong, Zhou, Jie, Qiao, Yu, Dai, Jifeng
Large language models (LLMs) have notably accelerated progress towards artificial general intelligence (AGI), with their impressive zero-shot capacity for user-tailored tasks, endowing them with immense potential across a range of applications. Howev
Externí odkaz:
http://arxiv.org/abs/2305.11175