Depth self-supervision for single image novel view synthesis
This addresses the problem of generating novel viewpoints from single images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles single-image novel view synthesis by jointly optimizing for view synthesis and depth estimation using a shared depth decoder trained with self-supervision. The approach improves both generated image quality and target viewpoint depth accuracy.
In this paper, we tackle the problem of generating a novel image from an arbitrary viewpoint given a single frame as input. While existing methods operating in this setup aim at predicting the target view depth map to guide the synthesis, without explicit supervision over such a task, we jointly optimize our framework for both novel view synthesis and depth estimation to unleash the synergy between the two at its best. Specifically, a shared depth decoder is trained in a self-supervised manner to predict depth maps that are consistent across the source and target views. Our results demonstrate the effectiveness of our approach in addressing the challenges of both tasks allowing for higher-quality generated images, as well as more accurate depth for the target viewpoint.