Zobrazeno 1 - 10
of 1 884
pro vyhledávání: '"DAI Qionghai"'
Gaussian splatting has gained attention for its efficient representation and rendering of 3D scenes using continuous Gaussian primitives. However, it struggles with sparse-view inputs due to limited geometric and photometric information, causing ambi
Externí odkaz:
http://arxiv.org/abs/2412.05908
Autor:
Yang, Runzhao, Chen, Yinda, Zhang, Zhihong, Liu, Xiaoyu, Li, Zongren, He, Kunlun, Xiong, Zhiwei, Suo, Jinli, Dai, Qionghai
In the field of medical image compression, Implicit Neural Representation (INR) networks have shown remarkable versatility due to their flexible compression ratios, yet they are constrained by a one-to-one fitting approach that results in lengthy enc
Externí odkaz:
http://arxiv.org/abs/2405.16850
Autor:
Jin, Yitong, Qiu, Zhiping, Shi, Yi, Sun, Shuangpeng, Wang, Chongwu, Pan, Donghao, Zhao, Jiachen, Liang, Zhenghao, Wang, Yuan, Li, Xiaobing, Yu, Feng, Yu, Tao, Dai, Qionghai
In this paper, we touch on the problem of markerless multi-modal human motion capture especially for string performance capture which involves inherently subtle hand-string contacts and intricate movements. To fulfill this goal, we first collect a da
Externí odkaz:
http://arxiv.org/abs/2405.04963
Video snapshot compressive imaging (SCI) encodes the target dynamic scene compactly into a snapshot and reconstructs its high-speed frame sequence afterward, greatly reducing the required data footprint and transmission bandwidth as well as enabling
Externí odkaz:
http://arxiv.org/abs/2404.07551
In this paper, we consider a novel and practical case for talking face video generation. Specifically, we focus on the scenarios involving multi-people interactions, where the talking context, such as audience or surroundings, is present. In these si
Externí odkaz:
http://arxiv.org/abs/2402.18092
Event cameras or dynamic vision sensors (DVS) record asynchronous response to brightness changes instead of conventional intensity frames, and feature ultra-high sensitivity at low bandwidth. The new mechanism demonstrates great advantages in challen
Externí odkaz:
http://arxiv.org/abs/2401.03153
The demand for compact cameras capable of recording high-speed scenes with high resolution is steadily increasing. However, achieving such capabilities often entails high bandwidth requirements, resulting in bulky, heavy systems unsuitable for low-ca
Externí odkaz:
http://arxiv.org/abs/2311.13134
This paper proposes a method for fast scene radiance field reconstruction with strong novel view synthesis performance and convenient scene editing functionality. The key idea is to fully utilize semantic parsing and primitive extraction for constrai
Externí odkaz:
http://arxiv.org/abs/2309.17190
This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation. The key idea is to first formally separate the foreground and the b
Externí odkaz:
http://arxiv.org/abs/2309.01374
Solving partial differential equations (PDEs) has been a fundamental problem in computational science and of wide applications for both scientific and engineering research. Due to its universal approximation property, neural network is widely used to
Externí odkaz:
http://arxiv.org/abs/2305.10033