Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines

• URL: http://arxiv.org/abs/2108.07408v2
• Date: Wed, 18 Aug 2021 12:29:40 GMT
• Title: Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines
• Authors: Mantang Guo, Jing Jin, Hui Liu, Junhui Hou
• Abstract summary: We propose a learnable model, namely dynamic reconstruction, to replace the commonly-used geometry warping operation. Experiments show that the reconstructed LF weights achieve much higher PSNR/SSIM and preserve the LF parallax structure better than state-of-the-art methods.
• Score: 42.59723383219793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we tackle the problem of dense light field (LF) reconstruction from sparsely-sampled ones with wide baselines and propose a learnable model, namely dynamic interpolation, to replace the commonly-used geometry warping operation. Specifically, with the estimated geometric relation between input views, we first construct a lightweight neural network to dynamically learn weights for interpolating neighbouring pixels from input views to synthesize each pixel of novel views independently. In contrast to the fixed and content-independent weights employed in the geometry warping operation, the learned interpolation weights implicitly incorporate the correspondences between the source and novel views and adapt to different image content information. Then, we recover the spatial correlation between the independently synthesized pixels of each novel view by referring to that of input views using a geometry-based spatial refinement module. We also constrain the angular correlation between the novel views through a disparity-oriented LF structure loss. Experimental results on LF datasets with wide baselines show that the reconstructed LFs achieve much higher PSNR/SSIM and preserve the LF parallax structure better than state-of-the-art methods. The source code is publicly available at https://github.com/MantangGuo/DI4SLF.

Related papers

• Physics-Informed Ensemble Representation for Light-Field Image Super-Resolution [12.156009287223382]
  We analyze the coordinate transformation of the light field (LF) imaging process to reveal the geometric relationship in the LF images. We introduce a new LF subspace of virtual-slit images (VSI) that provide sub-pixel information complementary to sub-aperture images. To super-resolve image structures from undersampled LF data, we propose a geometry-aware decoder, named EPIXformer.
  arXiv  Detail & Related papers  (2023-05-31T16:27:00Z)
• Explicit Correspondence Matching for Generalizable Neural Radiance Fields [49.49773108695526]
  We present a new NeRF method that is able to generalize to new unseen scenarios and perform novel view synthesis with as few as two source views. The explicit correspondence matching is quantified with the cosine similarity between image features sampled at the 2D projections of a 3D point on different views. Our method achieves state-of-the-art results on different evaluation settings, with the experiments showing a strong correlation between our learned cosine feature similarity and volume density.
  arXiv  Detail & Related papers  (2023-04-24T17:46:01Z)
• Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution [36.69391399634076]
  Exploiting spatial-angular correlation is crucial to light field (LF) image super-resolution (SR) We propose a simple yet effective method to learn the non-local spatial-angular correlation for LF image SR. Our method can fully incorporate the information from all angular views while achieving a global receptive field along the epipolar line.
  arXiv  Detail & Related papers  (2023-02-16T03:40:40Z)
• RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning [62.86400614141706]
  We propose a new learning model, i.e., Rectangling Rectification Network (RecRecNet) Our model can flexibly warp the source structure to the target domain and achieves an end-to-end unsupervised deformation. Experiments show the superiority of our solution over the compared methods on both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2023-01-04T15:12:57Z)
• PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis [52.546998369121354]
  We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images. We propose to incorporate explicit geometry reasoning and combine it with pixel-aligned features for radiance field prediction. We show that the introduction of such geometry-aware features helps to achieve a better disentanglement between appearance and geometry.
  arXiv  Detail & Related papers  (2022-02-10T07:39:47Z)
• Content-aware Warping for View Synthesis [110.54435867693203]
  We propose content-aware warping, which adaptively learns the weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network. Based on this learnable warping module, we propose a new end-to-end learning-based framework for novel view synthesis from two source views. Experimental results on structured light field datasets with wide baselines and unstructured multi-view datasets show that the proposed method significantly outperforms state-of-the-art methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2022-01-22T11:35:05Z)
• EPI-based Oriented Relation Networks for Light Field Depth Estimation [13.120247042876175]
  We propose an end-to-end fully convolutional network (FCN) to estimate the depth value of the intersection point on the horizontal and vertical Epipolar Plane Image (EPI) We present a new feature-extraction module, called Oriented Relation Module (ORM), that constructs the relationship between the line orientations. To facilitate training, we also propose a refocusing-based data augmentation method to obtain different slopes from EPIs of the same scene point.
  arXiv  Detail & Related papers  (2020-07-09T03:39:09Z)
• Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization [99.96632216070718]
  Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution. The high-dimensional spatiality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. We propose a novel learning-based LF framework, in which each view of an LF image is first individually super-resolved.
  arXiv  Detail & Related papers  (2020-04-05T14:39:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.