Corpus ID: 233219786

BARF: Bundle-Adjusting Neural Radiance Fields

@article{Lin2021BARFBN,
  title={BARF: Bundle-Adjusting Neural Radiance Fields},
  author={Chen-Hsuan Lin and Wei-Chiu Ma and A. Torralba and S. Lucey},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.06405}
}
Neural Radiance Fields (NeRF) [30] have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of realworld scenes. One limitation of NeRF, however, is its requirement of accurate camera poses to learn the scene representations. In this paper, we propose Bundle-Adjusting Neural Radiance Fields (BARF) for training NeRF from imperfect (or even unknown) camera poses — the joint problem of learning neural 3D representations… Expand
MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras

References

SHOWING 1-10 OF 71 REFERENCES
D-NeRF: Neural Radiance Fields for Dynamic Scenes
pixelNeRF: Neural Radiance Fields from One or Few Images
NeRF++: Analyzing and Improving Neural Radiance Fields
NeRF-: Neural Radiance Fields Without Known Camera Parameters
Depth synthesis and local warps for plausible image-based navigation
Free View Synthesis
Stereo Magnification: Learning View Synthesis using Multiplane Images
Light field rendering
...
1
2
3
4
5
...