paper-with-me

홈 › Papers

ConTEXTure: Consistent Multiview Images to Texture

2024-07-15 · Jaehoon Ahn, Sumin Cho, Harim Jung, Kibeom Hong, Seonghoon Ban, Moon-Ryul Jung

We introduce ConTEXTure, a generative network designed to create a texture map/atlas for a given 3D mesh using images from multiple viewpoints. The process begins with generating a front-view image from a text prompt, such as 'Napoleon, front view', describing the 3D mesh. Additional images from different viewpoints are derived from this front-view image and camera poses relative to it. ConTEXTure builds upon the TEXTure network, which uses text prompts for six viewpoints (e.g., 'Napoleon, front view', 'Napoleon, left view', etc.). However, TEXTure often generates images for non-front viewpoints that do not accurately represent those viewpoints.To address this issue, we employ Zero123++, which generates multiple view-consistent images for the six specified viewpoints simultaneously, conditioned on the initial front-view image and the depth maps of the mesh for the six viewpoints. By utilizing these view-consistent images, ConTEXTure learns the texture atlas from all viewpoint images concurrently, unlike previous methods that do so sequentially. This approach ensures that the rendered images from various viewpoints, including back, side, bottom, and top, are free from viewpoint irregularities.

📄 PDF Abstract BibTeX arXiv:2407.10558

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Contextures: Representations from Contexts

2025-05-02 · Runtian Zhai, Kai Yang, Che-Ping Tsai, Burak Varici 외

Despite the empirical success of foundation models, we do not have a systematic characterization of the representations that these models learn. In this paper, we establish the contexture theory. It shows that a large cl…

Representation Learning

Contextures: The Mechanism of Representation Learning

2025-04-28 · Runtian Zhai

This dissertation establishes the contexture theory to mathematically characterize the mechanism of representation learning, or pretraining. Despite the remarkable empirical success of foundation models, it is not very c…

Representation LearningSelf-Supervised Learning

MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts

2026-03-16 · Zheng Zhang, Qinchuan Zhang, Yuteng Ye, Zhi Chen 외 arxiv

Generating high-quality textures for 3D assets is a challenging task. Existing multiview texture generation methods suffer from the multiview inconsistency and missing textures on unseen parts, while UV inpainting textur…

NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction

2022-10-13 · Yusen Wang, Zongcheng Li, Yu Jiang, Kaixuan Zhou 외

We present a novel neural surface reconstruction method called NeuralRoom for reconstructing room-sized indoor scenes directly from a set of 2D images. Recently, implicit neural representations have become a promising wa…

Indoor Scene ReconstructionSurface Reconstruction

FROMAT: Multiview Material Appearance Transfer via Few-Shot Self-Attention Adaptation

2025-12-10 · Hubert Kompanowski, Varun Jampani, Aaryaman Vasishta, Binh-Son Hua arxiv

Multiview diffusion models have rapidly emerged as a powerful tool for content creation with spatial consistency across viewpoints, offering rich visual realism without requiring explicit geometry and appearance represen…