Learning to Dehaze from Realistic Scene with A Fast Physics-based Dehazing Network

• URL: http://arxiv.org/abs/2004.08554v2
• Date: Tue, 22 Sep 2020 03:58:11 GMT
• Title: Learning to Dehaze from Realistic Scene with A Fast Physics-based Dehazing Network
• Authors: Ruoteng Li, Xiaoyi Zhang, Shaodi You and Yu Li
• Abstract summary: We present a new, large, and diverse dehazing dataset containing real outdoor scenes from High-Definition (HD) 3D movies. We also propose a light and reliable dehazing network inspired by the physics model. Our approach outperforms other methods by a large margin and becomes the new state-of-the-art method.
• Score: 26.92874873109654
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dehazing is a popular computer vision topic for long. A real-time dehazing method with reliable performance is highly desired for many applications such as autonomous driving. While recent learning-based methods require datasets containing pairs of hazy images and clean ground truth references, it is generally impossible to capture accurate ground truth in real scenes. Many existing works compromise this difficulty to generate hazy images by rendering the haze from depth on common RGBD datasets using the haze imaging model. However, there is still a gap between the synthetic datasets and real hazy images as large datasets with high-quality depth are mostly indoor and depth maps for outdoor are imprecise. In this paper, we complement the existing datasets with a new, large, and diverse dehazing dataset containing real outdoor scenes from High-Definition (HD) 3D movies. We select a large number of high-quality frames of real outdoor scenes and render haze on them using depth from stereo. Our dataset is more realistic than existing ones and we demonstrate that using this dataset greatly improves the dehazing performance on real scenes. In addition to the dataset, we also propose a light and reliable dehazing network inspired by the physics model. Our approach outperforms other methods by a large margin and becomes the new state-of-the-art method. Moreover, the light-weight design of the network enables our method to run at a real-time speed, which is much faster than other baseline methods.

Related papers

• LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Dataset [14.141433473509826]
  We present LMHaze, a large-scale, high-quality real-world dataset. LMHaze comprises paired hazy and haze-free images captured in diverse indoor and outdoor environments. To better handle images with different haze intensities, we propose a mixture-of-experts model based on Mamba.
  arXiv  Detail & Related papers  (2024-10-21T15:20:02Z)
• Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience [28.651514326042648]
  We have built a custom mobile multi-camera large-space dense light field capture system. Our aim is to contribute to the development of popular 3D scene reconstruction algorithms. The collected dataset is much denser than existing datasets.
  arXiv  Detail & Related papers  (2024-03-15T02:39:44Z)
• EvaSurf: Efficient View-Aware Implicit Textured Surface Reconstruction on Mobile Devices [53.28220984270622]
  We present an implicit textured $textbfSurf$ace reconstruction method on mobile devices. Our method can reconstruct high-quality appearance and accurate mesh on both synthetic and real-world datasets. Our method can be trained in just 1-2 hours using a single GPU and run on mobile devices at over 40 FPS (Frames Per Second)
  arXiv  Detail & Related papers  (2023-11-16T11:30:56Z)
• HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction [37.29140654256627]
  We present a photo-realistic object-centric dataset HM3D-ABO. It is constructed by composing realistic indoor scene and realistic object. The dataset could also be useful for tasks such as camera pose estimation and novel-view synthesis.
  arXiv  Detail & Related papers  (2022-06-24T16:02:01Z)
• RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis [104.53930611219654]
  We present a large-scale synthetic dataset for novel view synthesis consisting of 300k images rendered from nearly 2000 complex scenes. The dataset is orders of magnitude larger than existing synthetic datasets for novel view synthesis. Using 4 distinct sources of high-quality 3D meshes, the scenes of our dataset exhibit challenging variations in camera views, lighting, shape, materials, and textures.
  arXiv  Detail & Related papers  (2022-05-14T13:15:32Z)
• Learning Dynamic View Synthesis With Few RGBD Cameras [60.36357774688289]
  We propose to utilize RGBD cameras to synthesize free-viewpoint videos of dynamic indoor scenes. We generate point clouds from RGBD frames and then render them into free-viewpoint videos via a neural feature. We introduce a simple Regional Depth-Inpainting module that adaptively inpaints missing depth values to render complete novel views.
  arXiv  Detail & Related papers  (2022-04-22T03:17:35Z)
• Stereo Matching by Self-supervision of Multiscopic Vision [65.38359887232025]
  We propose a new self-supervised framework for stereo matching utilizing multiple images captured at aligned camera positions. A cross photometric loss, an uncertainty-aware mutual-supervision loss, and a new smoothness loss are introduced to optimize the network. Our model obtains better disparity maps than previous unsupervised methods on the KITTI dataset.
  arXiv  Detail & Related papers  (2021-04-09T02:58:59Z)
• OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets [103.54691385842314]
  We propose a novel framework for creating large-scale photorealistic datasets of indoor scenes. Our goal is to make the dataset creation process widely accessible. This enables important applications in inverse rendering, scene understanding and robotics.
  arXiv  Detail & Related papers  (2020-07-25T06:48:47Z)
• Neural Sparse Voxel Fields [151.20366604586403]
  We introduce Neural Sparse Voxel Fields (NSVF), a new neural scene representation for fast and high-quality free-viewpoint rendering. NSVF defines a set of voxel-bounded implicit fields organized in a sparse voxel octree to model local properties in each cell. Our method is typically over 10 times faster than the state-of-the-art (namely, NeRF(Mildenhall et al., 2020)) at inference time while achieving higher quality results.
  arXiv  Detail & Related papers  (2020-07-22T17:51:31Z)
• A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset [6.319667056655425]
  We present a synthetic aerial dataset, called the WHU dataset, which is the first large-scale multi-view aerial dataset. We also introduce in this paper a novel network, called RED-Net, for wide-range depth inference. Our experiments confirmed that not only did our method exceed the current state-of-the-art MVS methods by more than 50% mean absolute error (MAE) with less memory and computational cost, but its efficiency as well.
  arXiv  Detail & Related papers  (2020-03-02T03:04:13Z)

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.