We present a method for generating consistent novel views from a single source image. Our approach focuses on maximizing the reuse of visible pixels from the source image. To achieve this, we use a monocular depth estimator that transfers visible pixels from the source view to the target view. Starting from a pre-trained 2D inpainting diffusion model, we train our method on the large-scale Objaverse dataset to learn 3D object priors. While training we use a novel masking mechanism based on epipolar lines to further improve the quality of our approach. This allows our framework to perform zero-shot novel view synthesis on a variety of objects. We evaluate the zero-shot abilities of our framework on three challenging datasets: Google Scanned Objects, Ray Traced Multiview, and Common Objects in 3D. See our webpage for more details: https://yashkant.github.io/invs/
@article{arxiv.2310.16167,
title = {iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis},
author = {Yash Kant and Aliaksandr Siarohin and Michael Vasilkovsky and Riza Alp Guler and Jian Ren and Sergey Tulyakov and Igor Gilitschenski},
journal= {arXiv preprint arXiv:2310.16167},
year = {2023}
}
Comments
Accepted to SIGGRAPH Asia, 2023 (Conference Papers)