Zobrazeno 1 - 10
of 389
pro vyhledávání: '"Wei, Guoqiang"'
We propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models. Unlike previous work, our method does not require any supervised finetuning on camera-annotated datasets or self-supervised trai
Externí odkaz:
http://arxiv.org/abs/2406.10126
Generating rich and controllable motion is a pivotal challenge in video synthesis. We propose Boximator, a new approach for fine-grained motion control. Boximator introduces two constraint types: hard box and soft box. Users select objects in the con
Externí odkaz:
http://arxiv.org/abs/2402.01566
Diffusion models have attained remarkable success in the domains of image generation and editing. It is widely recognized that employing larger inversion and denoising steps in diffusion model leads to improved image reconstruction quality. However,
Externí odkaz:
http://arxiv.org/abs/2312.15707
Creating high-dynamic videos such as motion-rich actions and sophisticated visual effects poses a significant challenge in the field of artificial intelligence. Unfortunately, current state-of-the-art video generation methods, primarily focusing on t
Externí odkaz:
http://arxiv.org/abs/2311.10982
Autor:
Zeng, Yan, Zhang, Hanbo, Zheng, Jiani, Xia, Jiangnan, Wei, Guoqiang, Wei, Yang, Zhang, Yuchen, Kong, Tao
Recent advancements in Large Language Models (LLMs) such as GPT4 have displayed exceptional multi-modal capabilities in following open-ended instructions given images. However, the performance of these models heavily relies on design choices such as
Externí odkaz:
http://arxiv.org/abs/2307.02469
Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities, which restrict their applicability in representing multiple scenes using a single model. To address this problem, existing generalizable NeRF methods simply condition th
Externí odkaz:
http://arxiv.org/abs/2304.04962
Vision transformer has demonstrated great potential in abundant vision tasks. However, it also inevitably suffers from poor generalization capability when the distribution shift occurs in testing (i.e., out-of-distribution data). To mitigate this iss
Externí odkaz:
http://arxiv.org/abs/2212.02739
The three existing dominant network families, i.e., CNNs, Transformers, and MLPs, differ from each other mainly in the ways of fusing spatial contextual information, leaving designing more effective token-mixing mechanisms at the core of backbone arc
Externí odkaz:
http://arxiv.org/abs/2203.06108
Publikováno v:
In Optik July 2024 307
Confounders in deep learning are in general detrimental to model's generalization where they infiltrate feature representations. Therefore, learning causal features that are free of interference from confounders is important. Most previous causal lea
Externí odkaz:
http://arxiv.org/abs/2111.13420