Diffusion-based Light Field Synthesis

• URL: http://arxiv.org/abs/2402.00575v1
• Date: Thu, 1 Feb 2024 13:13:16 GMT
• Title: Diffusion-based Light Field Synthesis
• Authors: Ruisheng Gao, Yutong Liu, Zeyu Xiao, Zhiwei Xiong
• Abstract summary: LFdiff is a diffusion-based generative framework tailored for LF synthesis. We propose DistgUnet, a disentanglement-based noise estimation network, to harness comprehensive LF representations. Extensive experiments demonstrate that LFdiff excels in synthesizing visually pleasing and disparity-controllable light fields.
• Score: 50.24624071354433
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Light fields (LFs), conducive to comprehensive scene radiance recorded across angular dimensions, find wide applications in 3D reconstruction, virtual reality, and computational photography.However, the LF acquisition is inevitably time-consuming and resource-intensive due to the mainstream acquisition strategy involving manual capture or laborious software synthesis.Given such a challenge, we introduce LFdiff, a straightforward yet effective diffusion-based generative framework tailored for LF synthesis, which adopts only a single RGB image as input.LFdiff leverages disparity estimated by a monocular depth estimation network and incorporates two distinctive components: a novel condition scheme and a noise estimation network tailored for LF data.Specifically, we design a position-aware warping condition scheme, enhancing inter-view geometry learning via a robust conditional signal.We then propose DistgUnet, a disentanglement-based noise estimation network, to harness comprehensive LF representations.Extensive experiments demonstrate that LFdiff excels in synthesizing visually pleasing and disparity-controllable light fields with enhanced generalization capability.Additionally, comprehensive results affirm the broad applicability of the generated LF data, spanning applications like LF super-resolution and refocusing.

Related papers

• LGFN: Lightweight Light Field Image Super-Resolution using Local Convolution Modulation and Global Attention Feature Extraction [5.461017270708014]
  We propose a lightweight model named LGFN which integrates the local and global features of different views and the features of different channels for LF image SR. Our model has a parameter of 0.45M and a FLOPs of 19.33G which has achieved a competitive effect.
  arXiv  Detail & Related papers  (2024-09-26T11:53:25Z)
• Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors [52.195637608631955]
  Non-line-of-sight (NLOS) imaging has attracted increasing attention due to its potential applications. Existing NLOS reconstruction approaches are constrained by the reliance on empirical physical priors. We introduce a novel learning-based solution, comprising two key designs: Learnable Path Compensation (LPC) and Adaptive Phasor Field (APF)
  arXiv  Detail & Related papers  (2024-09-21T04:39:45Z)
• LFIC-DRASC: Deep Light Field Image Compression Using Disentangled Representation and Asymmetrical Strip Convolution [51.909036244222904]
  We propose an end-to-end deep LF Image Compression method using Disentangled Representation and Asymmetrical Strip Convolution. Experimental results demonstrate that the proposed LFIC-DRASC achieves an average of 20.5% bit rate reductions.
  arXiv  Detail & Related papers  (2024-09-18T05:33:42Z)
• LFSRDiff: Light Field Image Super-Resolution via Diffusion Models [18.20217829625834]
  Light field (LF) image super-resolution (SR) is a challenging problem due to its inherent ill-posed nature. mainstream LF image SR methods typically adopt a deterministic approach, generating only a single output supervised by pixel-wise loss functions. We introduce LFSRDiff, the first diffusion-based LF image SR model, by incorporating the LF disentanglement mechanism.
  arXiv  Detail & Related papers  (2023-11-27T07:31:12Z)
• Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network [52.77569396659629]
  This paper presents the deep compensation network unfolding (DCUNet) for restoring light field (LF) images captured under low-light conditions. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. To properly leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module.
  arXiv  Detail & Related papers  (2023-08-10T07:53:06Z)
• Disentangling Light Fields for Super-Resolution and Disparity Estimation [67.50796924758221]
  Light field (LF) cameras record both intensity and directions of light rays, and encode 3D scenes into 4D LF images. It is challenging for convolutional neural networks (CNNs) to process LF images since the spatial and angular information are highly inter-twined with varying disparities. We propose a generic mechanism to disentangle these coupled information for LF image processing.
  arXiv  Detail & Related papers  (2022-02-22T01:04:41Z)
• Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering [9.893045525907219]
  Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence. With the popularization of commercial light field (LF) cameras, capturing LF images (LFIs) is as convenient as taking regular photos, and geometry information can be reliably inferred. We propose a novel scale-consistent volume rescaling algorithm that robustly aligns the disparity probability volumes (DPV) among different captures for scale-consistent global geometry fusion.
  arXiv  Detail & Related papers  (2021-06-17T14:27:08Z)
• Deep Selective Combinatorial Embedding and Consistency Regularization for Light Field Super-resolution [93.95828097088608]
  Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution. The high-dimensionality 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 spatial SR framework to explore the coherence among LF sub-aperture images. Experimental results over both synthetic and real-world LF datasets demonstrate the significant advantage of our approach over state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-09-26T08:34:37Z)

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.