Výsledky vyhledávání

Report

StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

Autor: Ye, Chongjie, Qiu, Lingteng, Gu, Xiaodong, Zuo, Qi, Wu, Yushuang, Dong, Zilong, Bo, Liefeng, Xiu, Yuliang, Han, Xiaoguang

This work addresses the challenge of high-quality surface normal estimation from monocular colored inputs (i.e., images and videos), a field which has recently been revolutionized by repurposing diffusion priors. However, previous attempts still stru

Externí odkaz: http://arxiv.org/abs/2406.16864

Zobrazit plný text záznamu

Report

An Optimization Framework to Enforce Multi-View Consistency for Texturing 3D Meshes

Autor: Zhao, Zhengyi, Song, Chen, Gu, Xiaodong, Dong, Yuan, Zuo, Qi, Yuan, Weihao, Bo, Liefeng, Dong, Zilong, Huang, Qixing

A fundamental problem in the texturing of 3D meshes using pre-trained text-to-image models is to ensure multi-view consistency. State-of-the-art approaches typically use diffusion models to aggregate multi-view inputs, where common issues are the blu

Externí odkaz: http://arxiv.org/abs/2403.15559

Zobrazit plný text záznamu

Report

VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model

Autor: Zuo, Qi, Gu, Xiaodong, Qiu, Lingteng, Dong, Yuan, Zhao, Zhengyi, Yuan, Weihao, Peng, Rui, Zhu, Siyu, Dong, Zilong, Bo, Liefeng, Huang, Qixing

Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency. This paper

Externí odkaz: http://arxiv.org/abs/2403.12010

Zobrazit plný text záznamu

Report

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D

Autor: Qiu, Lingteng, Chen, Guanying, Gu, Xiaodong, Zuo, Qi, Xu, Mutian, Wu, Yushuang, Yuan, Weihao, Dong, Zilong, Bo, Liefeng, Han, Xiaoguang

Lifting 2D diffusion for 3D generation is a challenging problem due to the lack of geometric prior and the complex entanglement of materials and lighting in natural images. Existing methods have shown promise by first creating the geometry through sc

Externí odkaz: http://arxiv.org/abs/2311.16918

Zobrazit plný text záznamu