Lightweight Deep Learning Architecture for MPI Correction and Transient Reconstruction

• URL: http://arxiv.org/abs/2111.14396v1
• Date: Mon, 29 Nov 2021 09:31:35 GMT
• Title: Lightweight Deep Learning Architecture for MPI Correction and Transient Reconstruction
• Authors: Adriano Simonetto, Gianluca Agresti, Pietro Zanuttigh and Henrik Sch\"afer
• Abstract summary: Indirect Time-of-Flight cameras (iToF) are low-cost devices that provide depth images at an interactive frame rate. They are affected by different error sources, with the spotlight taken by Multi-Path Interference (MPI) Common data-driven approaches tend to focus on a direct estimation of the output depth values, ignoring the underlying transient propagation of the light in the scene. We propose a very compact architecture, leveraging on the direct-global subdivision of transient information for the removal of MPI and for the reconstruction of the transient information itself.
• Score: 19.040317739792787
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Indirect Time-of-Flight cameras (iToF) are low-cost devices that provide depth images at an interactive frame rate. However, they are affected by different error sources, with the spotlight taken by Multi-Path Interference (MPI), a key challenge for this technology. Common data-driven approaches tend to focus on a direct estimation of the output depth values, ignoring the underlying transient propagation of the light in the scene. In this work instead, we propose a very compact architecture, leveraging on the direct-global subdivision of transient information for the removal of MPI and for the reconstruction of the transient information itself. The proposed model reaches state-of-the-art MPI correction performances both on synthetic and real data and proves to be very competitive also at extreme levels of noise; at the same time, it also makes a step towards reconstructing transient information from multi-frequency iToF data.

Related papers

• FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [63.87313550399871]
  Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability. We propose Self-supervised Transfer (PST) and FrequencyDe-coupled Fusion module (FreDF) PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models. FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.
  arXiv  Detail & Related papers  (2025-03-25T15:04:53Z)
• MFSR-GAN: Multi-Frame Super-Resolution with Handheld Motion Modeling [1.593690982728631]
  Smartphone cameras have become ubiquitous imaging tools, yet their small sensors and compact optics often limit spatial resolution. We introduce a novel synthetic data engine that uses multi-exposure static images to synthesize LR-HR training pairs. We also propose MFSR-GAN: a multi-scale RAW-to-RGB network for MFSR.
  arXiv  Detail & Related papers  (2025-02-28T08:11:03Z)
• Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators [83.48423407316713]
  We present a novel diffusion transformer framework incorporating an additional set of mediator tokens to engage with queries and keys separately. Our model initiates the denoising process with a precise, non-ambiguous stage and gradually transitions to a phase enriched with detail. Our method achieves a state-of-the-art FID score of 2.01 when integrated with the recent work SiT.
  arXiv  Detail & Related papers  (2024-08-11T07:01:39Z)
• Spatial-frequency Dual-Domain Feature Fusion Network for Low-Light Remote Sensing Image Enhancement [49.15531684596958]
  We propose a Dual-Domain Feature Fusion Network (DFFN) for low-light remote sensing image enhancement. The first phase learns amplitude information to restore image brightness, and the second phase learns phase information to refine details. We have constructed two dark light remote sensing datasets to address the current lack of datasets in dark light remote sensing image enhancement.
  arXiv  Detail & Related papers  (2024-04-26T13:21:31Z)
• Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction [18.014481087171657]
  The correction of exposure-related issues is a pivotal component in enhancing the quality of images. This paper proposes a novel methodology that leverages the frequency domain to improve and unify the handling of exposure correction tasks. Our proposed method achieves state-of-the-art results, paving the way for more sophisticated and unified solutions in exposure correction.
  arXiv  Detail & Related papers  (2023-09-03T14:09:14Z)
• 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)
• Blur Interpolation Transformer for Real-World Motion from Blur [52.10523711510876]
  We propose a encoded blur transformer (BiT) to unravel the underlying temporal correlation in blur. Based on multi-scale residual Swin transformer blocks, we introduce dual-end temporal supervision and temporally symmetric ensembling strategies. In addition, we design a hybrid camera system to collect the first real-world dataset of one-to-many blur-sharp video pairs.
  arXiv  Detail & Related papers  (2022-11-21T13:10:10Z)
• Wavelet-Based Network For High Dynamic Range Imaging [64.66969585951207]
  Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. In this work, we propose a novel frequency-guided end-to-end deep neural network (FNet) to conduct HDR fusion in the frequency domain, and Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details.
  arXiv  Detail & Related papers  (2021-08-03T12:26:33Z)
• iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imaging [26.17890136713725]
  Indirect Time-of-Flight (iToF) cameras are a promising depth sensing technology. They are prone to errors caused by multi-path interference (MPI) and low signal-to-noise ratio (SNR)
  arXiv  Detail & Related papers  (2021-03-12T04:57:52Z)
• Deep Burst Super-Resolution [165.90445859851448]
  We propose a novel architecture for the burst super-resolution task. Our network takes multiple noisy RAW images as input, and generates a denoised, super-resolved RGB image as output. In order to enable training and evaluation on real-world data, we additionally introduce the BurstSR dataset.
  arXiv  Detail & Related papers  (2021-01-26T18:57:21Z)
• Boosting Image Super-Resolution Via Fusion of Complementary Information Captured by Multi-Modal Sensors [21.264746234523678]
  Image Super-Resolution (SR) provides a promising technique to enhance the image quality of low-resolution optical sensors. In this paper, we attempt to leverage complementary information from a low-cost channel (visible/depth) to boost image quality of an expensive channel (thermal) using fewer parameters.
  arXiv  Detail & Related papers  (2020-12-07T02:15:28Z)
• Deep Non-Line-of-Sight Reconstruction [18.38481917675749]
  In this paper, we employ convolutional feed-forward networks for solving the reconstruction problem efficiently. We devise a tailored autoencoder architecture, trained end-to-end reconstruction maps transient images directly to a depth map representation. We demonstrate that our feed-forward network, even though it is trained solely on synthetic data, generalizes to measured data from SPAD sensors and is able to obtain results that are competitive with model-based reconstruction methods.
  arXiv  Detail & Related papers  (2020-01-24T16:05:50Z)

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.