no code implementations • 19 Apr 2024 • Longfei Huang, Shupeng Zhong, Xiangyu Wu, Ruoxuan Li
Subsequently, we propose caption-level strategy for the high-quality caption data generated by the image caption models and integrate them with retrieval augmentation strategy into the template to compel the model to generate higher quality, more matching, and semantically enriched captions based on the retrieval augmentation prompts.
1 code implementation • 2 Feb 2024 • Jinyuan Chang, Zhao Ding, Yuling Jiao, Ruoxuan Li, Jerry Zhijian Yang
We introduce an Ordinary Differential Equation (ODE) based deep generative method for learning a conditional distribution, named the Conditional Follmer Flow.
no code implementations • 30 Dec 2023 • Han Jiang, Haosen Sun, Ruoxuan Li, Chi-Keung Tang, Yu-Wing Tai
Second and the remaining problem is thus 3D multiview consistency among all completed images, now guided by the seed images and their 3D proxies.
no code implementations • 22 May 2023 • Han Jiang, Ruoxuan Li, Haosen Sun, Yu-Wing Tai, Chi-Keung Tang
No significant work has been done to directly merge two partially overlapping scenes using NeRF representations.