1Cognitive Learning for Vision and Robotics Lab, USC
2Carnegie Mellon University
3National Tsing Hua University, Taiwan
4Snap Inc.
We address the task of multi-view novel view synthesis, where we are interested in synthesizing a target image with an arbitrary camera pose from given source images. We propose an end-to-end trainable framework that learns to exploit multiple viewpoints to synthesize a novel view without any 3D supervision. Specifically, our model consists of a flow prediction module and a pixel generation module to directly leverage information presented in source views as well as hallucinate missing pixels from statistical priors. To merge the predictions produced by the two modules given multi-view source images, we introduce a self-learned confidence aggregation mechanism. We evaluate our model on images rendered from 3D object models as well as real and synthesized scenes. We demonstrate that our model is able to achieve state-of-the-art results as well as progressively improve its predictions when more source images are available.
We propose an end-to-end trainable framework that learns to exploit multiple viewpoints to synthesize a novel view without any 3D supervision. Specifically, our model consists of a flow prediction module (flow predictor) and a pixel generation module (recurrent pixel generator) to directly leverage information presented in source views as well as hallucinate missing pixels from statistical priors. To merge the predictions produced by the two modules given multi-view source images, we introduce a self-learned confidence aggregation mechanism. An illustration of the proposed framework is as follows.
More results for ShapeNet cars: link (1k randomly samlped results from all 10k testing data)
More results for ShapeNet chairs: link (1k randomly samlped results from all 10k testing data)
@inproceedings{sun2018multiview,
title = {Multi-view to Novel View: Synthesizing Novel Views with Self-Learned Confidence},
author = {Sun, Shao-Hua and Huh, Minyoung and Liao, Yuan-Hong and Zhang, Ning and Lim, Joseph J},
booktitle = {European Conference on Computer Vision},
year = {2018},
}
Check out some other work in novel view synthesis: