Learning optical flow from still images
- URL: http://arxiv.org/abs/2104.03965v1
- Date: Thu, 8 Apr 2021 17:59:58 GMT
- Title: Learning optical flow from still images
- Authors: Filippo Aleotti, Matteo Poggi, Stefano Mattoccia
- Abstract summary: We introduce a framework to generate accurate ground-truth optical flow annotations quickly and in large amounts from any readily available single real picture.
We virtually move the camera in the reconstructed environment with known motion vectors and rotation angles.
When trained with our data, state-of-the-art optical flow networks achieve superior generalization to unseen real data.
- Score: 53.295332513139925
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper deals with the scarcity of data for training optical flow
networks, highlighting the limitations of existing sources such as labeled
synthetic datasets or unlabeled real videos. Specifically, we introduce a
framework to generate accurate ground-truth optical flow annotations quickly
and in large amounts from any readily available single real picture. Given an
image, we use an off-the-shelf monocular depth estimation network to build a
plausible point cloud for the observed scene. Then, we virtually move the
camera in the reconstructed environment with known motion vectors and rotation
angles, allowing us to synthesize both a novel view and the corresponding
optical flow field connecting each pixel in the input image to the one in the
new frame. When trained with our data, state-of-the-art optical flow networks
achieve superior generalization to unseen real data compared to the same models
trained either on annotated synthetic datasets or unlabeled videos, and better
specialization if combined with synthetic images.
Related papers
- BVI-RLV: A Fully Registered Dataset and Benchmarks for Low-Light Video Enhancement [56.97766265018334]
This paper introduces a low-light video dataset, consisting of 40 scenes with various motion scenarios under two distinct low-lighting conditions.
We provide fully registered ground truth data captured in normal light using a programmable motorized dolly and refine it via an image-based approach for pixel-wise frame alignment across different light levels.
Our experimental results demonstrate the significance of fully registered video pairs for low-light video enhancement (LLVE) and the comprehensive evaluation shows that the models trained with our dataset outperform those trained with the existing datasets.
arXiv Detail & Related papers (2024-07-03T22:41:49Z) - Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability.
We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images.
Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
arXiv Detail & Related papers (2024-03-28T22:25:05Z) - OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation [55.676358801492114]
We propose OCAI, a method that supports robust frame ambiguities by generating intermediate video frames alongside optical flows in between.
Our evaluations demonstrate superior quality and enhanced optical flow accuracy on established benchmarks such as Sintel and KITTI.
arXiv Detail & Related papers (2024-03-26T20:23:48Z) - Skin the sheep not only once: Reusing Various Depth Datasets to Drive
the Learning of Optical Flow [25.23550076996421]
We propose to leverage the geometric connection between optical flow estimation and stereo matching.
We turn the monocular depth datasets into stereo ones via virtual disparity.
We also introduce virtual camera motion into stereo data to produce additional flows along the vertical direction.
arXiv Detail & Related papers (2023-10-03T06:56:07Z) - MPI-Flow: Learning Realistic Optical Flow with Multiplane Images [18.310665144874775]
We investigate generating realistic optical flow datasets from real-world images.
To generate highly realistic new images, we construct a layered depth representation, known as multiplane images (MPI), from single-view images.
To ensure the realism of motion, we present an independent object motion module that can separate the camera and dynamic object motion in MPI.
arXiv Detail & Related papers (2023-09-13T04:31:00Z) - RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos [28.995525297929348]
RealFlow is a framework that can create large-scale optical flow datasets directly from unlabeled realistic videos.
We first estimate optical flow between a pair of video frames, and then synthesize a new image from this pair based on the predicted flow.
Our approach achieves state-of-the-art performance on two standard benchmarks compared with both supervised and unsupervised optical flow methods.
arXiv Detail & Related papers (2022-07-22T13:33:03Z) - 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) - Optical Flow Dataset Synthesis from Unpaired Images [36.158607790844705]
We introduce a novel method to build a training set of pseudo-real images that can be used to train optical flow in a supervised manner.
Our dataset uses two unpaired frames from real data and creates pairs of frames by simulating random warps.
We thus obtain the benefit of directly training on real data while having access to an exact ground truth.
arXiv Detail & Related papers (2021-04-02T22:19:47Z) - Optical Flow Estimation from a Single Motion-blurred Image [66.2061278123057]
Motion blur in an image may have practical interests in fundamental computer vision problems.
We propose a novel framework to estimate optical flow from a single motion-blurred image in an end-to-end manner.
arXiv Detail & Related papers (2021-03-04T12:45:18Z) - Optical Flow in Dense Foggy Scenes using Semi-Supervised Learning [37.25344909016075]
We introduce a semi-supervised deep learning technique that employs real fog images without optical flow ground-truths in the training process.
We propose a new training strategy that combines supervised synthetic-data training and unsupervised real-data training.
Experimental results show that our method is effective and outperforms the state-of-the-art methods in estimating optical flow in dense foggy scenes.
arXiv Detail & Related papers (2020-04-04T10:44:16Z)
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.