MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References

1Department of Computer Science, ETH Zurich, Switzerland 2Microsoft Mixed Reality & AI Lab, Zurich, Switzerland
Interpolate start reference image.

We introduce MaRINeR: a pipeline taking as input a novel-view obtained from a 3D reconstruction exhibiting geometric and / or appearance artifacts and inaccuracies as well as a nearby reference used during the reconstruction process, and outputting an enhanced version of the novel-view through feature matching and transfer.

Results

LaMAR

Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR

Nerfacto

Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR

IBRnet

Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR
Rendering MaRINeR

Abstract

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.

Pipeline

Interpolate start reference image.

Video

BibTeX

@inproceedings{bösiger2024marinerenhancingnovelviews,
          title={MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References}, 
          author={Lukas Bösiger and Mihai Dusmanu and Marc Pollefeys and Zuria Bauer},
          year={2024},
          booktitle={European Conference on Computer Vision (ECCV)},
          url={https://arxiv.org/abs/2407.13745}, 
    }