Výsledky vyhledávání

Report

GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image

Autor: Bao, Chong, Zhang, Yinda, Li, Yuan, Zhang, Xiyu, Yang, Bangbang, Bao, Hujun, Pollefeys, Marc, Zhang, Guofeng, Cui, Zhaopeng

Recently, we have witnessed the explosive growth of various volumetric representations in modeling animatable head avatars. However, due to the diversity of frameworks, there is no practical method to support high-level applications like 3D head avat

Externí odkaz: http://arxiv.org/abs/2404.02152

Zobrazit plný text záznamu

Report

Mirror-NeRF: Learning Neural Radiance Fields for Mirrors with Whitted-Style Ray Tracing

Autor: Zeng, Junyi, Bao, Chong, Chen, Rui, Dong, Zilong, Zhang, Guofeng, Bao, Hujun, Cui, Zhaopeng

Recently, Neural Radiance Fields (NeRF) has exhibited significant success in novel view synthesis, surface reconstruction, etc. However, since no physical reflection is considered in its rendering pipeline, NeRF mistakes the reflection in the mirror

Externí odkaz: http://arxiv.org/abs/2308.03280

Zobrazit plný text záznamu

Report

SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field

Autor: Bao, Chong, Zhang, Yinda, Yang, Bangbang, Fan, Tianxing, Yang, Zesong, Bao, Hujun, Zhang, Guofeng, Cui, Zhaopeng

Despite the great success in 2D editing using user-friendly tools, such as Photoshop, semantic strokes, or even text prompts, similar capabilities in 3D areas are still limited, either relying on 3D modeling skills or allowing editing within only a f

Externí odkaz: http://arxiv.org/abs/2303.13277

Zobrazit plný text záznamu

Report

EC-SfM: Efficient Covisibility-based Structure-from-Motion for Both Sequential and Unordered Images

Autor: Ye, Zhichao, Bao, Chong, Zhou, Xin, Liu, Haomin, Bao, Hujun, Zhang, Guofeng

Structure-from-Motion is a technology used to obtain scene structure through image collection, which is a fundamental problem in computer vision. For unordered Internet images, SfM is very slow due to the lack of prior knowledge about image overlap.

Externí odkaz: http://arxiv.org/abs/2302.10544

Zobrazit plný text záznamu

Report

IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis

Autor: Ye, Weicai, Chen, Shuo, Bao, Chong, Bao, Hujun, Pollefeys, Marc, Cui, Zhaopeng, Zhang, Guofeng

Existing inverse rendering combined with neural rendering methods can only perform editable novel view synthesis on object-specific scenes, while we present intrinsic neural radiance fields, dubbed IntrinsicNeRF, which introduce intrinsic decompositi

Externí odkaz: http://arxiv.org/abs/2210.00647

Zobrazit plný text záznamu

Report

NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing

Autor: Yang, Bangbang, Bao, Chong, Zeng, Junyi, Bao, Hujun, Zhang, Yinda, Cui, Zhaopeng, Zhang, Guofeng

Very recently neural implicit rendering techniques have been rapidly evolved and shown great advantages in novel view synthesis and 3D scene reconstruction. However, existing neural rendering methods for editing purposes offer limited functionality,

Externí odkaz: http://arxiv.org/abs/2207.11911

Zobrazit plný text záznamu