Zobrazeno 1 - 10
of 582
pro vyhledávání: '"Jun, Kun"'
Autor:
Chen, Jun-Kun, Wang, Yu-Xiong
This paper proposes ProEdit - a simple yet effective framework for high-quality 3D scene editing guided by diffusion distillation in a novel progressive manner. Inspired by the crucial observation that multi-view inconsistency in scene editing is roo
Externí odkaz:
http://arxiv.org/abs/2411.05006
Autor:
Chen, Can, Wang, Jun-Kun
Developing algorithms to differentiate between machine-generated texts and human-written texts has garnered substantial attention in recent years. Existing methods in this direction typically concern an offline setting where a dataset containing a mi
Externí odkaz:
http://arxiv.org/abs/2410.22318
The creation of complex 3D scenes tailored to user specifications has been a tedious and challenging task with traditional 3D modeling tools. Although some pioneering methods have achieved automatic text-to-3D generation, they are generally limited t
Externí odkaz:
http://arxiv.org/abs/2410.09049
Thermodynamics of black holes offers a promising avenue for exploring the quantum nature of black holes and quantum gravity. In this Letter, we investigate the thermodynamic properties of dyonic black holes in the five-dimensional Einstein-Maxwell-Ch
Externí odkaz:
http://arxiv.org/abs/2410.00717
Autor:
Chen, Jun-Kun, Bulò, Samuel Rota, Müller, Norman, Porzi, Lorenzo, Kontschieder, Peter, Wang, Yu-Xiong
This paper proposes ConsistDreamer - a novel framework that lifts 2D diffusion models with 3D awareness and 3D consistency, thus enabling high-fidelity instruction-guided scene editing. To overcome the fundamental limitation of missing 3D consistency
Externí odkaz:
http://arxiv.org/abs/2406.09404
This paper proposes Instruct 4D-to-4D that achieves 4D awareness and spatial-temporal consistency for 2D diffusion models to generate high-quality instruction-guided dynamic scene editing results. Traditional applications of 2D diffusion models in dy
Externí odkaz:
http://arxiv.org/abs/2406.09402
Autor:
Wang, Jun-Kun
We propose an optimization algorithm called Hamiltonian Descent, which is a direct counterpart of classical Hamiltonian Monte Carlo in sampling. We find that Hamiltonian Descent for solving strongly convex quadratic problems exhibits a novel update s
Externí odkaz:
http://arxiv.org/abs/2402.13988
This paper proposes NeuralEditor that enables neural radiance fields (NeRFs) natively editable for general shape editing tasks. Despite their impressive results on novel-view synthesis, it remains a fundamental challenge for NeRFs to edit the shape o
Externí odkaz:
http://arxiv.org/abs/2305.03049
Autor:
Ruan, Bin-Bin, Chen, Le-Wei, Shi, Yun-Qing, Yi, Jun-Kun, Yang, Qing-Song, Zhou, Meng-Hu, Ma, Ming-Wei, Chen, Gen-Fu, Ren, Zhi-An
Publikováno v:
Journal of Physics: Condensed Matter 2023 35, 214002
We report the discovery and detailed investigation of superconductivity in Mo$_4$Ga$_{20}$As. Mo$_4$Ga$_{20}$As crystallizes in the space group of $I4/m$ (No. 87), with lattice parameters $a$ = 12.86352 \AA and $c$ = 5.30031 \AA. The resistivity, mag
Externí odkaz:
http://arxiv.org/abs/2305.02838
Autor:
Wang, Jun-Kun, Wibisono, Andre
Quasar convexity is a condition that allows some first-order methods to efficiently minimize a function even when the optimization landscape is non-convex. Previous works develop near-optimal accelerated algorithms for minimizing this class of functi
Externí odkaz:
http://arxiv.org/abs/2302.07851