Knowledge distillation (KD) has emerged as a promising technique in deep learning, typically employed to enhance a compact student network through learning from their high-performance but more complex teacher variant. When applied in the context of image super-resolution, most KD approaches are modified versions of methods developed for other computer vision tasks, which are based on training strategies with a single teacher and simple loss functions. In this paper, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) framework specifically for image super-resolution. It exploits the advantages of multiple teachers by combining and enhancing the outputs of these teacher models, which then guides the learning process of the compact student network. To achieve more effective learning performance, we have also developed a new wavelet-based loss function for MTKD, which can better optimize the training process by observing differences in both the spatial and frequency domains. We fully evaluate the effectiveness of the proposed method by comparing it to five commonly used KD methods for image super-resolution based on three popular network architectures. The results show that the proposed MTKD method achieves evident improvements in super-resolution performance, up to 0.46dB (based on PSNR), over state-of-the-art KD approaches across different network structures. The source code of MTKD will be made available here for public evaluation.
Visual Place Recognition (VPR) in indoor environments is beneficial to humans and robots for better localization and navigation. It is challenging due to appearance changes at various frequencies, and difficulties of obtaining ground truth metric trajectories for training and evaluation. This paper introduces the NYC-Indoor-VPR dataset, a unique and rich collection of over 36,000 images compiled from 13 distinct crowded scenes in New York City taken under varying lighting conditions with appearance changes. Each scene has multiple revisits across a year. To establish the ground truth for VPR, we propose a semiautomatic annotation approach that computes the positional information of each image. Our method specifically takes pairs of videos as input and yields matched pairs of images along with their estimated relative locations. The accuracy of this matching is refined by human annotators, who utilize our annotation software to correlate the selected keyframes. Finally, we present a benchmark evaluation of several state-of-the-art VPR algorithms using our annotated dataset, revealing its challenge and thus value for VPR research.
Adopting omnidirectional Field of View (FoV) cameras in aerial robots vastly improves perception ability, significantly advancing aerial robotics's capabilities in inspection, reconstruction, and rescue tasks. However, such sensors also elevate system complexity, e.g., hardware design, and corresponding algorithm, which limits researchers from utilizing aerial robots with omnidirectional FoV in their research. To bridge this gap, we propose OmniNxt, a fully open-source aerial robotics platform with omnidirectional perception. We design a high-performance flight controller NxtPX4 and a multi-fisheye camera set for OmniNxt. Meanwhile, the compatible software is carefully devised, which empowers OmniNxt to achieve accurate localization and real-time dense mapping with limited computation resource occupancy. We conducted extensive real-world experiments to validate the superior performance of OmniNxt in practical applications. All the hardware and software are open-access at https://github.com/HKUST-Aerial-Robotics/OmniNxt, and we provide docker images of each crucial module in the proposed system. Project page: https://hkust-aerial-robotics.github.io/OmniNxt.
Lithic Use-Wear Analysis (LUWA) using microscopic images is an underexplored vision-for-science research area. It seeks to distinguish the worked material, which is critical for understanding archaeological artifacts, material interactions, tool functionalities, and dental records. However, this challenging task goes beyond the well-studied image classification problem for common objects. It is affected by many confounders owing to the complex wear mechanism and microscopic imaging, which makes it difficult even for human experts to identify the worked material successfully. In this paper, we investigate the following three questions on this unique vision task for the first time:(i) How well can state-of-the-art pre-trained models (like DINOv2) generalize to the rarely seen domain? (ii) How can few-shot learning be exploited for scarce microscopic images? (iii) How do the ambiguous magnification and sensing modality influence the classification accuracy? To study these, we collaborated with archaeologists and built the first open-source and the largest LUWA dataset containing 23,130 microscopic images with different magnifications and sensing modalities. Extensive experiments show that existing pre-trained models notably outperform human experts but still leave a large gap for improvements. Most importantly, the LUWA dataset provides an underexplored opportunity for vision and learning communities and complements existing image classification problems on common objects.
Surface prediction and completion have been widely studied in various applications. Recently, research in surface completion has evolved from small objects to complex large-scale scenes. As a result, researchers have begun increasing the volume of data and leveraging a greater variety of data modalities including rendered RGB images, descriptive texts, depth images, etc, to enhance algorithm performance. However, existing datasets suffer from a deficiency in the amounts of scene-level models along with the corresponding multi-modal information. Therefore, a method to scale the datasets and generate multi-modal information in them efficiently is essential. To bridge this research gap, we propose MASSTAR: a Multi-modal lArge-scale Scene dataset with a verSatile Toolchain for surfAce pRediction and completion. We develop a versatile and efficient toolchain for processing the raw 3D data from the environments. It screens out a set of fine-grained scene models and generates the corresponding multi-modal data. Utilizing the toolchain, we then generate an example dataset composed of over a thousand scene-level models with partial real-world data added. We compare MASSTAR with the existing datasets, which validates its superiority: the ability to efficiently extract high-quality models from complex scenarios to expand the dataset. Additionally, several representative surface completion algorithms are benchmarked on MASSTAR, which reveals that existing algorithms can hardly deal with scene-level completion. We will release the source code of our toolchain and the dataset. For more details, please see our project page at https://sysu-star.github.io/MASSTAR.
In this work we focus on learning facial representations that can be adapted to train effective face recognition models, particularly in the absence of labels. Firstly, compared with existing labelled face datasets, a vastly larger magnitude of unlabeled faces exists in the real world. We explore the learning strategy of these unlabeled facial images through self-supervised pretraining to transfer generalized face recognition performance. Moreover, motivated by one recent finding, that is, the face saliency area is critical for face recognition, in contrast to utilizing random cropped blocks of images for constructing augmentations in pretraining, we utilize patches localized by extracted facial landmarks. This enables our method - namely LAndmark-based Facial Self-supervised learning LAFS), to learn key representation that is more critical for face recognition. We also incorporate two landmark-specific augmentations which introduce more diversity of landmark information to further regularize the learning. With learned landmark-based facial representations, we further adapt the representation for face recognition with regularization mitigating variations in landmark positions. Our method achieves significant improvement over the state-of-the-art on multiple face recognition benchmarks, especially on more challenging few-shot scenarios.
A robot's ability to anticipate the 3D action target location of a hand's movement from egocentric videos can greatly improve safety and efficiency in human-robot interaction (HRI). While previous research predominantly focused on semantic action classification or 2D target region prediction, we argue that predicting the action target's 3D coordinate could pave the way for more versatile downstream robotics tasks, especially given the increasing prevalence of headset devices. This study expands EgoPAT3D, the sole dataset dedicated to egocentric 3D action target prediction. We augment both its size and diversity, enhancing its potential for generalization. Moreover, we substantially enhance the baseline algorithm by introducing a large pre-trained model and human prior knowledge. Remarkably, our novel algorithm can now achieve superior prediction outcomes using solely RGB images, eliminating the previous need for 3D point clouds and IMU input. Furthermore, we deploy our enhanced baseline algorithm on a real-world robotic platform to illustrate its practical utility in straightforward HRI tasks. The demonstrations showcase the real-world applicability of our advancements and may inspire more HRI use cases involving egocentric vision. All code and data are open-sourced and can be found on the project website.
Collaborative perception leverages rich visual observations from multiple robots to extend a single robot's perception ability beyond its field of view. Many prior works receive messages broadcast from all collaborators, leading to a scalability challenge when dealing with a large number of robots and sensors. In this work, we aim to address \textit{scalable camera-based collaborative perception} with a Transformer-based architecture. Our key idea is to enable a single robot to intelligently discern the relevance of the collaborators and their associated cameras according to a learned spatial prior. This proactive understanding of the visual features' relevance does not require the transmission of the features themselves, enhancing both communication and computation efficiency. Specifically, we present ActFormer, a Transformer that learns bird's eye view (BEV) representations by using predefined BEV queries to interact with multi-robot multi-camera inputs. Each BEV query can actively select relevant cameras for information aggregation based on pose information, instead of interacting with all cameras indiscriminately. Experiments on the V2X-Sim dataset demonstrate that ActFormer improves the detection performance from 29.89% to 45.15% in terms of AP@0.7 with about 50% fewer queries, showcasing the effectiveness of ActFormer in multi-agent collaborative 3D object detection.
This paper tackles the challenge of autonomous target search using unmanned aerial vehicles (UAVs) in complex unknown environments. To fill the gap in systematic approaches for this task, we introduce Star-Searcher, an aerial system featuring specialized sensor suites, mapping, and planning modules to optimize searching. Path planning challenges due to increased inspection requirements are addressed through a hierarchical planner with a visibility-based viewpoint clustering method. This simplifies planning by breaking it into global and local sub-problems, ensuring efficient global and local path coverage in real-time. Furthermore, our global path planning employs a history-aware mechanism to reduce motion inconsistency from frequent map changes, significantly enhancing search efficiency. We conduct comparisons with state-of-the-art methods in both simulation and the real world, demonstrating shorter flight paths, reduced time, and higher target search completeness. Our approach will be open-sourced for community benefit at https://github.com/SYSU-STAR/STAR-Searcher.