most citedInNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields

4 citations · 6 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2023★ 4 cited

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

Dongqing Wang, Tong Zhang, Alaa Abboud +1

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 objec…

cs.CV2023

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

Dongqing Wang, Tong Zhang, Sabine Süsstrunk

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 m…