← Search

Dongqing Wang

2 accepted papers

2024

InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields

CVPR 2024poster

We propose InNeRF360 an automatic system that accurately removes text-specified objects from 360-degree Neural Radiance Fields (NeRF). The challenge is to effectively remove objects while inpainting perceptually consistent content for the missing regions which is particularly demanding for existing…

2023

NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects

ICCV 2023poster

We propose NEMTO, the first end-to-end neural rendering pipeline to model 3D transparent objects with complex geometry and unknown indices of refraction. Commonly used appearance modeling such as the Disney BSDF model cannot accurately address this challenging problem due to the complex light paths…

Cited by 12PDFcodeScholar