Zobrazeno 1 - 10
of 459
pro vyhledávání: '"McKinnon, David"'
Autor:
Chen, Hongkai, Luo, Zixin, Tian, Yurun, Bai, Xuyang, Wang, Ziyu, Zhou, Lei, Zhen, Mingmin, Fang, Tian, McKinnon, David, Tsin, Yanghai, Quan, Long
Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks. Recent semi-dense matching methods emphasize the effectiveness of fusing relevant cross-view information
Externí odkaz:
http://arxiv.org/abs/2405.13874
Let $X$ be a smooth projective algebraic variety over a number field $k$ and $P$ in $X(k)$. In 2007, the second author conjectured that, in a precise sense, if rational points on $X$ are dense enough, then the best rational approximations to $P$ must
Externí odkaz:
http://arxiv.org/abs/2403.02480
Autor:
Lu, Yuanxun, Zhang, Jingyang, Li, Shiwei, Fang, Tian, McKinnon, David, Tsin, Yanghai, Quan, Long, Cao, Xun, Yao, Yao
Recent advances in generative AI have unveiled significant potential for the creation of 3D content. However, current methods either apply a pre-trained 2D diffusion model with the time-consuming score distillation sampling (SDS), or a direct 3D diff
Externí odkaz:
http://arxiv.org/abs/2311.15980
Autor:
Zhang, Jingyang, Li, Shiwei, Lu, Yuanxun, Fang, Tian, McKinnon, David, Tsin, Yanghai, Quan, Long, Yao, Yao
We introduce JointNet, a novel neural network architecture for modeling the joint distribution of images and an additional dense modality (e.g., depth maps). JointNet is extended from a pre-trained text-to-image diffusion model, where a copy of the o
Externí odkaz:
http://arxiv.org/abs/2310.06347
Autor:
McKinnon, David
We compute the constant of approximation for an arbitrary rational point on an arbitrary smooth cubic hypersurface $X$ over a number field $k$, provided that there is a $k$-rational line somewhere on $X$. In the process, we verify the Coba conjecture
Externí odkaz:
http://arxiv.org/abs/2310.01640
Autor:
Zhang, Jingyang, Yao, Yao, Li, Shiwei, Liu, Jingbo, Fang, Tian, McKinnon, David, Tsin, Yanghai, Quan, Long
We present a novel differentiable rendering framework for joint geometry, material, and lighting estimation from multi-view images. In contrast to previous methods which assume a simplified environment map or co-located flashlights, in this work, we
Externí odkaz:
http://arxiv.org/abs/2303.17147
Autor:
Chen, Hongkai, Luo, Zixin, Zhou, Lei, Tian, Yurun, Zhen, Mingmin, Fang, Tian, Mckinnon, David, Tsin, Yanghai, Quan, Long
Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we propose ASpanFormer, a Transformer-based detector-free matcher that is bui
Externí odkaz:
http://arxiv.org/abs/2208.14201
Autor:
Zhang, Jingyang, Yao, Yao, Li, Shiwei, Fang, Tian, McKinnon, David, Tsin, Yanghai, Quan, Long
Neural implicit functions have recently shown promising results on surface reconstructions from multiple views. However, current methods still suffer from excessive time complexity and poor robustness when reconstructing unbounded or complex scenes.
Externí odkaz:
http://arxiv.org/abs/2206.03087
Publikováno v:
Physical Review Physics Education Research, 18(1), 010117
This paper presents a new astronomy self efficacy instrument, composed of two factors, one relating to learning astronomy content, which we call astronomy personal self efficacy, and the other relating to the use of astronomical instrumentation, spec
Externí odkaz:
http://arxiv.org/abs/2204.13803
Autor:
Yao, Yao, Zhang, Jingyang, Liu, Jingbo, Qu, Yihang, Fang, Tian, McKinnon, David, Tsin, Yanghai, Quan, Long
We present a differentiable rendering framework for material and lighting estimation from multi-view images and a reconstructed geometry. In the framework, we represent scene lightings as the Neural Incident Light Field (NeILF) and material propertie
Externí odkaz:
http://arxiv.org/abs/2203.07182