When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation

• URL: http://arxiv.org/abs/2206.13850v1
• Date: Tue, 28 Jun 2022 09:29:55 GMT
• Title: When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation
• Authors: Madhu Vankadari, Stuart Golodetz, Sourav Garg, Sangyun Shin, Andrew Markham, Niki Trigoni
• Abstract summary: We show how to use a combination of three techniques to allow the existing photometric losses to work for both day and nighttime images. First, we introduce a per-pixel neural intensity transformation to compensate for the light changes that occur between successive frames. Second, we predict a per-pixel residual flow map that we use to correct the reprojection correspondences induced by the estimated ego-motion and depth.
• Score: 47.617222712429026
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Self-supervised deep learning methods for joint depth and ego-motion estimation can yield accurate trajectories without needing ground-truth training data. However, as they typically use photometric losses, their performance can degrade significantly when the assumptions these losses make (e.g. temporal illumination consistency, a static scene, and the absence of noise and occlusions) are violated. This limits their use for e.g. nighttime sequences, which tend to contain many point light sources (including on dynamic objects) and low signal-to-noise ratio (SNR) in darker image regions. In this paper, we show how to use a combination of three techniques to allow the existing photometric losses to work for both day and nighttime images. First, we introduce a per-pixel neural intensity transformation to compensate for the light changes that occur between successive frames. Second, we predict a per-pixel residual flow map that we use to correct the reprojection correspondences induced by the estimated ego-motion and depth from the networks. And third, we denoise the training images to improve the robustness and accuracy of our approach. These changes allow us to train a single model for both day and nighttime images without needing separate encoders or extra feature networks like existing methods. We perform extensive experiments and ablation studies on the challenging Oxford RobotCar dataset to demonstrate the efficacy of our approach for both day and nighttime sequences.

Related papers

• bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction [57.199618102578576]
  We propose bit2bit, a new method for reconstructing high-quality image stacks at original resolution from sparse binary quantatemporal image data. Inspired by recent work on Poisson denoising, we developed an algorithm that creates a dense image sequence from sparse binary photon data. We present a novel dataset containing a wide range of real SPAD high-speed videos under various challenging imaging conditions.
  arXiv  Detail & Related papers  (2024-10-30T17:30:35Z)
• Transientangelo: Few-Viewpoint Surface Reconstruction Using Single-Photon Lidar [8.464054039931245]
  Lidar captures 3D scene geometry by emitting pulses of light to a target and recording the speed-of-light time delay of the reflected light. conventional lidar systems do not output the raw, captured waveforms of backscattered light. We develop new regularization strategies that improve robustness to photon noise, enabling accurate surface reconstruction with as few as 10 photons per pixel.
  arXiv  Detail & Related papers  (2024-08-22T08:12:09Z)
• Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensation [24.382795861986803]
  Using night images for self-supervision is unreliable because the photometric consistency assumption is usually violated in the videos taken under complex lighting conditions. We propose a self-supervised nighttime monocular depth estimation method that does not use any night images during training.
  arXiv  Detail & Related papers  (2024-04-22T03:39:03Z)
• Exposure Bracketing is All You Need for Unifying Image Restoration and Enhancement Tasks [50.822601495422916]
  We propose to utilize exposure bracketing photography to unify image restoration and enhancement tasks. Due to the difficulty in collecting real-world pairs, we suggest a solution that first pre-trains the model with synthetic paired data. In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed.
  arXiv  Detail & Related papers  (2024-01-01T14:14:35Z)
• Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery [69.71080926778413]
  flare artifacts can affect image visual quality and downstream computer vision tasks. Current methods do not consider automatic exposure and tone mapping in image signal processing pipeline. We propose a solution to improve the performance of lens flare removal by revisiting the ISP and design a more reliable light sources recovery strategy.
  arXiv  Detail & Related papers  (2023-08-31T04:58:17Z)
• Deep Dynamic Scene Deblurring from Optical Flow [53.625999196063574]
  Deblurring can provide visually more pleasant pictures and make photography more convenient. It is difficult to model the non-uniform blur mathematically. We develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features.
  arXiv  Detail & Related papers  (2023-01-18T06:37:21Z)
• Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences using Transformer Networks [23.6427456783115]
  In this work, we focus on outdoor lighting estimation by aggregating individual noisy estimates from images. Recent work based on deep neural networks has shown promising results for single image lighting estimation, but suffers from robustness. We tackle this problem by combining lighting estimates from several image views sampled in the angular and temporal domain of an image sequence.
  arXiv  Detail & Related papers  (2022-02-18T14:11:16Z)
• Invertible Network for Unpaired Low-light Image Enhancement [78.33382003460903]
  We propose to leverage the invertible network to enhance low-light image in forward process and degrade the normal-light one inversely with unpaired learning. In addition to the adversarial loss, we design various loss functions to ensure the stability of training and preserve more image details. We present a progressive self-guided enhancement process for low-light images and achieve favorable performance against the SOTAs.
  arXiv  Detail & Related papers  (2021-12-24T17:00:54Z)
• Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation [17.066753214406525]
  We propose a domain-separated network for self-supervised depth estimation of all-day images. Our approach achieves state-of-the-art depth estimation results for all-day images on the challenging Oxford RobotCar dataset.
  arXiv  Detail & Related papers  (2021-08-17T13:52:19Z)
• Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation [17.067988025947024]
  We look into the problem of estimating per-pixel depth maps from unconstrained RGB monocular night-time images. The state-of-the-art day-time depth estimation methods fail miserably when tested with night-time images. We propose to solve this problem by posing it as a domain adaptation problem where a network trained with day-time images is adapted to work for night-time images.
  arXiv  Detail & Related papers  (2020-10-03T17:55:16Z)

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.