☆ 3.8 Proceedings Paper

Depth-supervised NeRF: Fewer Views and Faster Training for Free

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

Related references

Note: Only part of the references are listed.

Editorial Material Computer Science, Hardware & Architecture

Neural Radiance Fields Explode on the Scene

Frank Dellaert

COMMUNICATIONS OF THE ACM (2022)

Add to Collection

Article Computer Science, Software Engineering

Point-Based Neural Rendering with Per-View Optimization

T. Neff et al.

Summary: Recently, there has been a growing interest in neural rendering methods. This study introduces a general approach that utilizes MVS for initialization but allows further optimization of scene properties in the input view space, resulting in improved quality and speed in novel-view synthesis compared to previous methods.

COMPUTER GRAPHICS FORUM (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

Yi Wei et al.

Summary: In this work, a new multi-view depth estimation method is proposed, utilizing both conventional SfM reconstruction and learning-based priors over NeRF. The method directly optimizes over implicit volumes, guided by adapted depth priors, improving depth quality significantly in indoor scenes. The approach combines the advantages of correspondence-based optimization and NeRF-based optimization, without sacrificing the original synthesis capability of neural radiance fields.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence