Výsledky vyhledávání

Report

Autor: Gu, Chun, Yang, Zeyu, Pan, Zijie, Zhu, Xiatian, Zhang, Li

3D representation is essential to the significant advance of 3D generation with 2D diffusion priors. As a flexible representation, NeRF has been first adopted for 3D representation. With density-based volumetric rendering, it however suffers both int

Externí odkaz: http://arxiv.org/abs/2406.01579

Zobrazit plný text záznamu

Report

Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models

Autor: Yang, Zeyu, Pan, Zijie, Gu, Chun, Zhang, Li

Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models. These models are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of producing high

Externí odkaz: http://arxiv.org/abs/2404.02148

Zobrazit plný text záznamu

Report

Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering

Autor: Chen, Yurui, Gu, Chun, Jiang, Junzhe, Zhu, Xiatian, Zhang, Li

Modeling dynamic, large-scale urban scenes is challenging due to their highly intricate geometric structures and unconstrained dynamics in both space and time. Prior methods often employ high-level architectural priors, separating static and dynamic

Externí odkaz: http://arxiv.org/abs/2311.18561

Zobrazit plný text záznamu

Report

Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing

Autor: Gao, Jian, Gu, Chun, Lin, Youtian, Li, Zhihao, Zhu, Hao, Cao, Xun, Zhang, Li, Yao, Yao

In this paper, we present a novel differentiable point-based rendering framework to achieve photo-realistic relighting. To make the reconstructed scene relightable, we enhance vanilla 3D Gaussians by associating extra properties, including normal vec

Externí odkaz: http://arxiv.org/abs/2311.16043

Zobrazit plný text záznamu

Report

Single-view Neural Radiance Fields with Depth Teacher

Autor: Chen, Yurui, Gu, Chun, Zhang, Feihu, Zhang, Li

Neural Radiance Fields (NeRF) have been proposed for photorealistic novel view rendering. However, it requires many different views of one scene for training. Moreover, it has poor generalizations to new scenes and requires retraining or fine-tuning

Externí odkaz: http://arxiv.org/abs/2303.09952

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání