Zobrazeno 1 - 10
of 1 984
pro vyhledávání: '"Šída, P."'
Autor:
Xie, Tao, Chen, Xi, Xu, Zhen, Xie, Yiman, Jin, Yudong, Shen, Yujun, Peng, Sida, Bao, Hujun, Zhou, Xiaowei
Reconstructing complex reflections in real-world scenes from 2D images is essential for achieving photorealistic novel view synthesis. Existing methods that utilize environment maps to model reflections from distant lighting often struggle with high-
Externí odkaz:
http://arxiv.org/abs/2412.15215
Autor:
Zhou, Chenxu, Fu, Lvchang, Peng, Sida, Yan, Yunzhi, Zhang, Zhanhua, Chen, Yong, Xia, Jiazhi, Zhou, Xiaowei
This paper targets the challenge of real-time LiDAR re-simulation in dynamic driving scenarios. Recent approaches utilize neural radiance fields combined with the physical modeling of LiDAR sensors to achieve high-fidelity re-simulation results. Unfo
Externí odkaz:
http://arxiv.org/abs/2412.15199
This paper calculates the stochastic gravitational wave background from dark binaries with finite-range attractive dark forces, complementing previous works which consider long-range dark forces. The finiteness of the dark force range can dramaticall
Externí odkaz:
http://arxiv.org/abs/2412.15158
Autor:
Lin, Haotong, Peng, Sida, Chen, Jingxiao, Peng, Songyou, Sun, Jiaming, Liu, Minghuan, Bao, Hujun, Feng, Jiashi, Zhou, Xiaowei, Kang, Bingyi
Prompts play a critical role in unleashing the power of language and vision foundation models for specific tasks. For the first time, we introduce prompting into depth foundation models, creating a new paradigm for metric depth estimation termed Prom
Externí odkaz:
http://arxiv.org/abs/2412.14015
Autor:
Yan, Yunzhi, Xu, Zhen, Lin, Haotong, Jin, Haian, Guo, Haoyu, Wang, Yida, Zhan, Kun, Lang, Xianpeng, Bao, Hujun, Zhou, Xiaowei, Peng, Sida
This paper aims to tackle the problem of photorealistic view synthesis from vehicle sensor data. Recent advancements in neural scene representation have achieved notable success in rendering high-quality autonomous driving scenes, but the performance
Externí odkaz:
http://arxiv.org/abs/2412.13188
Autor:
Pi, Huaijin, Guo, Ruoxi, Shen, Zehong, Shuai, Qing, Hu, Zechen, Wang, Zhumei, Dong, Yajiao, Hu, Ruizhen, Komura, Taku, Peng, Sida, Zhou, Xiaowei
Text-driven human motion synthesis is capturing significant attention for its ability to effortlessly generate intricate movements from abstract text cues, showcasing its potential for revolutionizing motion design not only in film narratives but als
Externí odkaz:
http://arxiv.org/abs/2412.13111
With the advancement of pre-trained vision-language (VL) models, enhancing the alignment between visual and linguistic modalities in downstream tasks has emerged as a critical challenge. Different from existing fine-tuning methods that add extra modu
Externí odkaz:
http://arxiv.org/abs/2412.10817
This paper aims to address the challenge of reconstructing long volumetric videos from multi-view RGB videos. Recent dynamic view synthesis methods leverage powerful 4D representations, like feature grids or point cloud sequences, to achieve high-qua
Externí odkaz:
http://arxiv.org/abs/2412.09608
Autor:
Fu, Xiao, Liu, Xian, Wang, Xintao, Peng, Sida, Xia, Menghan, Shi, Xiaoyu, Yuan, Ziyang, Wan, Pengfei, Zhang, Di, Lin, Dahua
This paper aims to manipulate multi-entity 3D motions in video generation. Previous methods on controllable video generation primarily leverage 2D control signals to manipulate object motions and have achieved remarkable synthesis results. However, 2
Externí odkaz:
http://arxiv.org/abs/2412.07759
Autor:
Ou, Ke, Perez-Ramirez, Victor M., Cao, Sida, Redshaw, Caleb, Lee, Jin, Wang, Michelle M., Mikhailova, Julia M., Michel, Pierre, Edwards, Matthew R.
This letter presents a spatial filter based on saturated absorption in gas as a replacement for the solid pinhole in a lens-pinhole-lens filtering system. We show that an ultraviolet laser pulse focused through ozone will have its spatial profile cle
Externí odkaz:
http://arxiv.org/abs/2412.02770