相关论文: The Devil in the Details: Simple and Effective Opt…

With the recent success of deep neural networks, remarkable progress has been achieved on face recognition. However, collecting large-scale real-world training data for face recognition has turned out to be challenging, especially due to…

Dichotomous Image Segmentation (DIS) tasks require highly precise annotations, and traditional dataset creation methods are labor intensive, costly, and require extensive domain expertise. Although using synthetic data for DIS is a…

Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and large amounts of data, a common practice is to download models…

Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem…

Recent advances in diffusion and flow-based generative models have demonstrated remarkable success in image restoration tasks, achieving superior perceptual quality compared to traditional deep learning approaches. However, these methods…

In recent years, interest in synthetic data has grown, particularly in the context of pre-training the image modality to support a range of computer vision tasks, including object classification, medical imaging etc. Previous work has…

Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly:…

We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be…

Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical…

Using huge training datasets can be costly and inconvenient. This article explores various data distillation techniques that can reduce the amount of data required to successfully train deep networks. Inspired by recent ideas, we suggest…

Gesture recognition research, unlike NLP, continues to face acute data scarcity, with progress constrained by the need for costly human recordings or image processing approaches that cannot generate authentic variability in the gestures…

The optical flow of natural scenes is a combination of the motion of the observer and the independent motion of objects. Existing algorithms typically focus on either recovering motion and structure under the assumption of a purely static…

For low-level computer vision and image processing ML tasks, training on large datasets is critical for generalization. However, the standard practice of relying on real-world images primarily from the Internet comes with image quality,…

This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters. A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields. Due to…

State-of-the-art face recognition networks are often computationally expensive and cannot be used for mobile applications. Training lightweight face recognition models also requires large identity-labeled datasets. Meanwhile, there are…

Optical flow estimation is a challenging problem remaining unsolved. Recent deep learning based optical flow models have achieved considerable success. However, these models often train networks from the scratch on standard optical flow…

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers…

Building high-quality datasets for specialized tasks is a time-consuming and resource-intensive process that often requires specialized domain knowledge. We propose Corpus Retrieval and Augmentation for Fine-Tuning (CRAFT), a method for…

While recent methods for motion and stereo estimation recover an unprecedented amount of details, such highly detailed structures are neither adequately reflected in the data of existing benchmarks nor their evaluation methodology. Hence,…

Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data…