相关论文: A Closer Look at Invariances in Self-supervised Pr…

Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough…

Single-view depth estimation refers to the ability to derive three-dimensional information per pixel from a single two-dimensional image. Single-view depth estimation is an ill-posed problem because there are multiple depth solutions that…

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

Spatial reasoning on multi-view line drawings by state-of-the-art supervised deep networks is recently shown with puzzling low performances on the SPARE3D dataset. Based on the fact that self-supervised learning is helpful when a large…

Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well…

In this paper, we study the importance of pre-training for the generalization capability in the color constancy problem. We propose two novel approaches based on convolutional autoencoders: an unsupervised pre-training algorithm using a…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: self-supervised learning for Vision Transformers (ViT). While the training…

3D photography renders a static image into a video with appealing 3D visual effects. Existing approaches typically first conduct monocular depth estimation, then render the input frame to subsequent frames with various viewpoints, and…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

3D object representation learning is a fundamental challenge in computer vision to infer about the 3D world. Recent advances in deep learning have shown their efficiency in 3D object recognition, among which view-based methods have…

Viewpoint invariance remains challenging for visual recognition in the 3D world, as altering the viewing directions can significantly impact predictions for the same object. While substantial efforts have been dedicated to making neural…

The significant achievements of pre-trained models leveraging large volumes of data in the field of NLP and 2D vision inspire us to explore the potential of extensive data pre-training for 3D perception in autonomous driving. Toward this…

Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of self-supervised…

We propose a self-supervised learning framework that uses unlabeled monocular video sequences to generate large-scale supervision for training a Visual Odometry (VO) frontend, a network which computes pointwise data associations across…

Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale. In this paper, we…

Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models. In this paper, we find that existing contrastive learning based solutions for self-supervised video recognition focus on…

Recent work on visual representation learning has shown to be efficient for robotic manipulation tasks. However, most existing works pretrained the visual backbone solely on 2D images or egocentric videos, ignoring the fact that robots…

Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses. In contrast, we propose an approach that can exploit…

We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences. Existing unsupervised methods often exploit brightness constancy and…