paper-with-me

홈 › Papers

3D-aware Blending with Generative NeRFs

2023-02-13 · ICCV 2023 1 · Hyunsu Kim, Gayoung Lee, Yunjey Choi, Jin-Hwa Kim, Jun-Yan Zhu

Image blending aims to combine multiple images seamlessly. It remains challenging for existing 2D-based methods, especially when input images are misaligned due to differences in 3D camera poses and object shapes. To tackle these issues, we propose a 3D-aware blending method using generative Neural Radiance Fields (NeRF), including two key components: 3D-aware alignment and 3D-aware blending. For 3D-aware alignment, we first estimate the camera pose of the reference image with respect to generative NeRFs and then perform 3D local alignment for each part. To further leverage 3D information of the generative NeRF, we propose 3D-aware blending that directly blends images on the NeRF's latent representation space, rather than raw pixel space. Collectively, our method outperforms existing 2D baselines, as validated by extensive quantitative and qualitative evaluations with FFHQ and AFHQ-Cat.

📄 PDF Abstract BibTeX arXiv:2302.06608

Code (1)

naver-ai/BlendNeRF 공식 구현 pytorch

Tasks

NeRF

Similar Papers 제목 키워드 기반

NeRFuser: Large-Scale Scene Representation by NeRF Fusion

2023-05-22 · Jiading Fang, Shengjie Lin, Igor Vasiljevic, Vitor Guizilini 외

A practical benefit of implicit visual representations like Neural Radiance Fields (NeRFs) is their memory efficiency: large scenes can be efficiently stored and shared as small neural nets instead of collections of imag…

NeRF

SeamlessNeRF: Stitching Part NeRFs with Gradient Propagation

2023-10-30 · Bingchen Gong, Yuehao Wang, Xiaoguang Han, Qi Dou

Neural Radiance Fields (NeRFs) have emerged as promising digital mediums of 3D objects and scenes, sparking a surge in research to extend the editing capabilities in this domain. The task of seamless editing and merging …

Blending Distributed NeRFs with Tri-stage Robust Pose Optimization

2024-05-05 · Baijun Ye, Caiyun Liu, Xiaoyu Ye, Yuantao Chen 외

Due to the limited model capacity, leveraging distributed Neural Radiance Fields (NeRFs) for modeling extensive urban environments has become a necessity. However, current distributed NeRF registration approaches encount…

NeRFPose Estimation

Generating Part-Aware Editable 3D Shapes Without 3D Supervision

2023-01-01 · CVPR 2023 1 · Konstantinos Tertikas, Despoina Paschalidou, Boxiao Pan, Jeong Joon Park 외

Impressive progress in generative models and implicit representations gave rise to methods that can generate 3D shapes of high quality. However, being able to locally control and edit shapes is another essential prop…

NeRF

PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision

2023-03-16 · Konstantinos Tertikas, Despoina Paschalidou, Boxiao Pan, Jeong Joon Park 외

Impressive progress in generative models and implicit representations gave rise to methods that can generate 3D shapes of high quality. However, being able to locally control and edit shapes is another essential property…

NeRF