Vehicle Make and Model Recognition (VMMR) systems provide a fully automatic framework to recognize and classify different vehicle models. Several approaches have been proposed to address this challenge; however, they can perform in restricted conditions. Here, in this paper, we formulate the VMMR as a fine-grained classification problem and propose a new configurable on-road VMMR framework. We benefit from the unsupervised feature learning methods, and in more details, we employ Locality-constraint Linear Coding (LLC) method as a fast feature encoder for encoding the input SIFT features. The proposed method can perform in real environments of different conditions. This framework can recognize 50 models of vehicles and has the advantage to classify every other vehicle not belonging to one of the specified 50 classes as an unknown vehicle. The proposed VMMR framework can be configured to become faster or more accurate based on the application domain. The proposed approach is examined on two datasets, including Iranian on-road vehicle (IORV) dataset and CompuCar dataset. The IORV dataset contains images of 50 models of vehicles captured in real situations by traffic-cameras in different weather and lighting conditions. The experimental results show the advantage of the real-time configuration of the proposed framework over the state-of-the-art methods on the IORV datatset and comparable results on CompuCar dataset with 97.5% and 98.4% accuracies, respectively and acceptable running time.
Deflectometry is a key component in the precise measurement of specular (mirrored) surfaces; however, traditional methods often lack an end-to-end approach that performs 3D reconstruction in a single shot with high accuracy and generalizes across different free-form surfaces. This paper introduces a novel deep neural network (DNN)-based approach for end-to-end 3D reconstruction of free-form specular surfaces using single-shot deflectometry. Our proposed network, VUDNet, innovatively combines discriminative and generative components to accurately interpret orthogonal fringe patterns and generate high-fidelity 3D surface reconstructions. By leveraging a hybrid architecture integrating a Variational Autoencoder (VAE) and a modified U-Net, VUDNet excels in both depth estimation and detail refinement, achieving superior performance in challenging environments. Extensive data simulation using Blender leading to a dataset which we will make available, ensures robust training and enables the network to generalize across diverse scenarios. Experimental results demonstrate the strong performance of VUDNet, setting a new standard for 3D surface reconstruction.
27 December 2025 in Computer Vision and Image Understanding
Recent state-of-the-art semi-supervised Video Object Segmentation (VOS) methods have shown significant improvements in target object segmentation accuracy when information from preceding frames is used in segmenting the current frame. In particular, such memory-based approaches can help a model to more effectively handle appearance changes (representation drift) or occlusions. Ideally, for maximum performance, Online VOS methods would need all or most of the preceding frames (or their extracted information) to be stored in memory and be used for online learning in later frames. Such a solution is not feasible for long videos, as the required memory size grows without bound, and such methods can fail when memory is limited and a target object experiences repeated representation drifts over time. We propose two novel techniques to reduce the memory requirement of Online VOS methods while improving modeling accuracy and generalization on long videos. Motivated by the success of continual learning techniques in preserving previously-learned knowledge, here we propose Gated-Regularizer Continual Learning (GRCL), which improves the performance of any Online VOS subject to limited memory, and a Reconstruction-based Memory Selection Continual Learning (RMSCL), which empowers Online VOS methods to efficiently benefit from stored information in memory. We also analyze the performance of a hybrid combination of the two proposed methods. Experimental results show that the proposed methods are able to improve the performance of Online VOS models by more than 8%, with improved robustness on long-video datasets while maintaining comparable performance on short-video datasets such as DAVIS16, DAVIS17, and YouTube-VOS18.
Continual learning in real-world scenarios is a major challenge. A general continual learning model should have a constant memory size and no predefined task boundaries, as is the case in semi-supervised Video Object Segmentation (VOS), where continual learning challenges particularly present themselves in working on long video sequences. In this article, we first formulate the problem of semi-supervised VOS, specifically online VOS, as a continual learning problem, and then secondly provide a public VOS dataset, CLVOS23, focusing on continual learning. Finally, we propose and implement a regularization-based continual learning approach on LWL, an existing online VOS baseline, to demonstrate the efficacy of continual learning when applied to online VOS and to establish a CLVOS23 baseline. We apply the proposed baseline to the Long Videos dataset as well as to two short video VOS datasets, DAVIS16 and DAVIS17. To the best of our knowledge, this is the first time that VOS has been defined and addressed as a continual learning problem.
Deflectometry is a key component in the precise measurement of specular (mirrored) surfaces, however traditional methods often lack an end-to-end approach that performs 3D reconstruction in a single shot with high accuracy and generalizes across different free-form surfaces. This paper introduces a novel deep neural network (DNN)-based approach for end-to-end 3D reconstruction of free-form specular surfaces using single-shot deflectometry. Our proposed network, VUDNet, innovatively combines discriminative and generative components to accurately interpret orthogonal fringe patterns and generate high-fidelity 3D surface reconstructions. By leveraging a hybrid architecture integrating a Variational Autoencoder (VAE) and a modified U-Net, VUDNet excels in both depth estimation and detail refinement, achieving superior performance in challenging environments. Extensive data simulation using Blender, leading to a dataset which we are making available, ensures robust training and enables the network to generalize across diverse scenarios. Experimental results demonstrate the strong performance of VUDNet, setting a new standard for 3D surface reconstruction. The implementation of VUDNet is available on GitHub at https://github.com/hadious/VUDNet.