MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References
This addresses the need for realistic renderings in mixed-reality and autonomous agent training, though it is incremental as it builds on reference-based super-resolution networks.
The paper tackles the problem of low-quality novel view rendering from imperfect 3D reconstructions by proposing MaRINeR, a method that refines renderings using nearby reference images, resulting in improved quantitative metrics and qualitative examples.
Rendering realistic images from 3D reconstruction is an essential task of many Computer Vision and Robotics pipelines, notably for mixed-reality applications as well as training autonomous agents in simulated environments. However, the quality of novel views heavily depends of the source reconstruction which is often imperfect due to noisy or missing geometry and appearance. Inspired by the recent success of reference-based super-resolution networks, we propose MaRINeR, a refinement method that leverages information of a nearby mapping image to improve the rendering of a target viewpoint. We first establish matches between the raw rendered image of the scene geometry from the target viewpoint and the nearby reference based on deep features, followed by hierarchical detail transfer. We show improved renderings in quantitative metrics and qualitative examples from both explicit and implicit scene representations. We further employ our method on the downstream tasks of pseudo-ground-truth validation, synthetic data enhancement and detail recovery for renderings of reduced 3D reconstructions.