Learning to Adapt Multi-View Stereo by Self-Supervision
- URL: http://arxiv.org/abs/2009.13278v1
- Date: Mon, 28 Sep 2020 12:42:36 GMT
- Title: Learning to Adapt Multi-View Stereo by Self-Supervision
- Authors: Arijit Mallick, J\"org St\"uckler, Hendrik Lensch
- Abstract summary: 3D scene reconstruction from multiple views is an important classical problem in computer vision.
Deep learning based approaches have recently demonstrated impressive reconstruction results.
We propose an adaptive learning approach for multi-view stereo which trains a deep neural network for improved adaptability to new target domains.
- Score: 0.5156484100374059
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 3D scene reconstruction from multiple views is an important classical problem
in computer vision. Deep learning based approaches have recently demonstrated
impressive reconstruction results. When training such models, self-supervised
methods are favourable since they do not rely on ground truth data which would
be needed for supervised training and is often difficult to obtain. Moreover,
learned multi-view stereo reconstruction is prone to environment changes and
should robustly generalise to different domains. We propose an adaptive
learning approach for multi-view stereo which trains a deep neural network for
improved adaptability to new target domains. We use model-agnostic
meta-learning (MAML) to train base parameters which, in turn, are adapted for
multi-view stereo on new domains through self-supervised training. Our
evaluations demonstrate that the proposed adaptation method is effective in
learning self-supervised multi-view stereo reconstruction in new domains.
Related papers
- UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching [18.02254687807291]
UniTT-Stereo is a method to maximize the potential of Transformer-based stereo architectures.
State-of-the-art performance of UniTT-Stereo is validated on various benchmarks such as ETH3D, KITTI 2012, and KITTI 2015 datasets.
arXiv Detail & Related papers (2024-09-04T09:02:01Z) - Reusable Architecture Growth for Continual Stereo Matching [92.36221737921274]
We introduce a Reusable Architecture Growth (RAG) framework to learn new scenes continually in both supervised and self-supervised manners.
RAG can maintain high reusability during growth by reusing previous units while obtaining good performance.
We also present a Scene Router module to adaptively select the scene-specific architecture path at inference.
arXiv Detail & Related papers (2024-03-30T13:24:58Z) - PointFix: Learning to Fix Domain Bias for Robust Online Stereo
Adaptation [67.41325356479229]
We propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix.
In a nutshell, our auxiliary network learns to fix local variants intensively by effectively back-propagating local information through the meta-gradient.
This network is model-agnostic, so can be used in any kind of architectures in a plug-and-play manner.
arXiv Detail & Related papers (2022-07-27T07:48:29Z) - Deep Learning for Multi-View Stereo via Plane Sweep: A Survey [0.0]
3D reconstruction has lately attracted increasing attention due to its wide application in many areas, such as autonomous driving, robotics and virtual reality.
As a dominant technique in artificial intelligence, deep learning has been successfully adopted to solve various computer vision problems.
This paper presents a review of recent progress in deep learning methods for Multi-view Stereo (MVS), which is considered as a crucial task of image-based 3D reconstruction.
arXiv Detail & Related papers (2021-06-18T14:10:44Z) - Single-Layer Vision Transformers for More Accurate Early Exits with Less
Overhead [88.17413955380262]
We introduce a novel architecture for early exiting based on the vision transformer architecture.
We show that our method works for both classification and regression problems.
We also introduce a novel method for integrating audio and visual modalities within early exits in audiovisual data analysis.
arXiv Detail & Related papers (2021-05-19T13:30:34Z) - Deep Multi-View Stereo gone wild [12.106051690920266]
Deep multi-view stereo (deep MVS) methods have been developed and extensively compared on simple datasets.
In this paper, we ask whether the conclusions reached in controlled scenarios are still valid when working with Internet photo collections.
We propose a methodology for evaluation and explore the influence of three aspects of deep MVS methods: network architecture, training data, and supervision.
arXiv Detail & Related papers (2021-04-30T17:07:17Z) - Multi-Domain Adversarial Feature Generalization for Person
Re-Identification [52.835955258959785]
We propose a multi-dataset feature generalization network (MMFA-AAE)
It is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to unseen' camera systems.
It also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin.
arXiv Detail & Related papers (2020-11-25T08:03:15Z) - Reversing the cycle: self-supervised deep stereo through enhanced
monocular distillation [51.714092199995044]
In many fields, self-supervised learning solutions are rapidly evolving and filling the gap with supervised approaches.
We propose a novel self-supervised paradigm reversing the link between the two.
In order to train deep stereo networks, we distill knowledge through a monocular completion network.
arXiv Detail & Related papers (2020-08-17T07:40:22Z) - Continual Adaptation for Deep Stereo [52.181067640300014]
We propose a continual adaptation paradigm for deep stereo networks designed to deal with challenging and ever-changing environments.
In our paradigm, the learning signals needed to continuously adapt models online can be sourced from self-supervision via right-to-left image warping or from traditional stereo algorithms.
Our network architecture and adaptation algorithms realize the first real-time self-adaptive deep stereo system.
arXiv Detail & Related papers (2020-07-10T08:15:58Z)
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.