In autonomous driving, thermal image semantic segmentation has emerged as a critical research area, owing to its ability to provide robust scene understanding under adverse visual conditions. In particular, unsupervised domain adaptation (UDA) for thermal image segmentation can be an efficient solution to address the lack of labeled thermal datasets. Nevertheless, since these methods do not effectively utilize the complementary information between RGB and thermal images, they significantly decrease performance during domain adaptation. In this paper, we present a comprehensive study on cross-spectral UDA for thermal image semantic segmentation. We first propose a novel masked mutual learning strategy that promotes complementary information exchange by selectively transferring results between each spectral model while masking out uncertain regions. Additionally, we introduce a novel prototypical self-supervised loss designed to enhance the performance of the thermal segmentation model in nighttime scenarios. This approach addresses the limitations of RGB pre-trained networks, which cannot effectively transfer knowledge under low illumination due to the inherent constraints of RGB sensors. In experiments, our method achieves higher performance over previous UDA methods and comparable performance to state-of-the-art supervised methods.

The rise of 4K XR displays has increased demand for highresolution content, raising network and computational costs. To address these challenges while preserving perceptual quality, this study proposes binocular asymmetric quality degradation, leveraging findings that perceived quality is dominated by the higherfidelity view and acuity differences between dominant and nondominant eyes. A total of 41 participants viewed four types of 4 K content (video clip, game, UI, web) under two conditions: both eyes receiving the original video, or one eye receiving a lower-resolution or higher-compression version. Participants selected which appeared higher in quality. Using the Just Objectionable Difference (JOD) scale, results indicated participants generally failed to notice quality degradation at one-third of the original resolution and across all tested compression levels. Content-specific differences emerged: for game content, resolution degradation was unnoticed at any level, whereas compression artifacts became noticeable from Constant Rate Factor (CRF) 60 onward. Additionally, comparing JOD values for dominant versus non-dominant eye-based asymmetric quality degradation revealed that preserving original resolution in the dominant eye improved perceived quality for UI content, whereas maintaining original compression quality in the dominant eye was more critical for game content. Finally, to evaluate the JOD results in an objective context, we examined the alignment between objective quality metrics and subjective asymmetry tolerances. Video Multi-Method Assessment Fusion (VMAF) showed the strongest correspondence; participants did not notice asymmetric quality degradation at a VMAF score of approximately 46.76, confirmed by an additional validation test. The study supports content-adaptive asymmetric quality degradation in XR to efficiently reduce computational overhead while maintaining visual fidelity.

Typical LiDAR-based 3D object detection models are trained with real-world data collection, which is often imbalanced over classes. To deal with it, augmentation techniques are commonly used, such as copying ground truth LiDAR points and pasting them into scenes. However, existing methods struggle with the lack of sample diversity for minority classes and the limitation of suitable placement. In this work, we introduce a novel approach that utilizes pseudo LiDAR point clouds generated from low-cost miniatures or real-world videos, which is called Pseudo Ground Truth augmentation (PGT-Aug). PGT-Aug involves three key steps: (i) volumetric 3D instance reconstruction using a 2D-to-3D view synthesis model, (ii) object-level domain alignment with LiDAR intensity simulation, and (iii) a hybrid context-aware placement method from ground and map information. We demonstrate the superiority and generality of our method through performance improvements in extensive experiments conducted on popular benchmarks, i.e., nuScenes, KITTI, and Lyft, especially for the datasets with large domain gaps captured by different LiDAR configurations. The project webpage is https://just-add-100-more.github.io.

Multispectral recognition has attracted increasing attention from the research community due to its potential competence for many applications from day to night. However, due to the domain shift between RGB and thermal image, it has still many challenges to apply and to use RGB domain-based tasks. To reduce the domain gap, we propose multispectral domain invariant framework, which leverages the unpaired image translation method to generate a semantic and strongly discriminative invariant image by enforcing novel constraints in the objective function. We demonstrate the efficacy of the proposed method on mainly multispectral place recognition task and achieve significant improvement compared to previous works. Furthermore, we test on multispectral semantic segmentation and unsupervised domain adaptations to prove the scalability and generality of the proposed method. We will open our source code and dataset.

Recent works on domain adaptation exploit adversarial training to obtain domain-invariant feature representations from the joint learning of feature extractor and domain discriminator networks. However, domain adversarial methods render suboptimal performances since they attempt to match the distributions among the domains without considering the task at hand. We propose Drop to Adapt (DTA), which leverages adversarial dropout to learn strongly discriminative features by enforcing the cluster assumption. Accordingly, we design objective functions to support robust domain adaptation. We demonstrate efficacy of the proposed method on various experiments and achieve consistent improvements in both image classification and semantic segmentation tasks. Our source code is available at https://github.com/postBG/DTA.pytorch.

In this paper, we tackle unsupervised domain adaptation, where a target domain is unlabeled and lies on a considerably different distribution from a source domain. To alleviate such data discrepancies, we coin a novel deep neural network architecture that consists of a classifier and a domain discriminator on top of a shared feature extractor. Toward efficient regularization, we delegate a generation of the adversarial attacks to the domain discriminator. We then leverage the domain adversarial images to let the classification network learn important semantic features across the domains. Specifically, we employ consistency loss function that enables the joint use of clean and adversarial data. We present extensive experimental results on various domain adaptation benchmarks to show the efficacy of the proposed method.

To understand the real-world, it is essential to perceive in all-day conditions including cases which are not suitable for RGB sensors, especially at night. Beyond these limitations, the innovation introduced here is a multispectral solution in the form of depth estimation from a thermal sensor without an additional depth sensor.Based on an analysis of multispectral properties and the relevance to depth predictions, we propose an efficient and novel multi-task framework called the Multispectral Transfer Network (MTN) to estimate a depth image from a single thermal image. By exploiting geometric priors and chromaticity clues, our model can generate a pixel-wise depth image in an unsupervised manner. Moreover, we propose a new type of multitask module called Interleaver as a means of incorporating the chromaticity and fine details of skip-connections into the depth estimation framework without sharing feature layers. Lastly, we explain a novel technical means of stably training and covering large disparities and extending thermal images to data-driven methods for all-day conditions. In experiments, we demonstrate the better performance and generalization of depth estimation through the proposed multispectral stereo dataset, including various driving conditions.

We introduce the KAIST multi-spectral data set, which covers a great range of drivable regions, from urban to residential, for autonomous systems. Our data set provides the different perspectives of the world captured in coarse time slots (day and night), in addition to fine time slots (sunrise, morning, afternoon, sunset, night, and dawn). For all-day perception of autonomous systems, we propose the use of a different spectral sensor, i.e., a thermal imaging camera. Toward this goal, we develop a multi-sensor platform, which supports the use of a co-aligned RGB/Thermal camera, RGB stereo, 3-D LiDAR, and inertial sensors (GPS/IMU) and a related calibration technique. We design a wide range of visual perception tasks including the object detection, drivable region detection, localization, image enhancement, depth estimation, and colorization using a single/multi-spectral approach. In this paper, we provide a description of our benchmark with the recording platform, data format, development toolkits, and lessons about the progress of capturing data sets.

In this paper, we propose a unified end-to-end trainable multi-task network that jointly handles lane and road marking detection and recognition that is guided by a vanishing point under adverse weather conditions. We tackle rainy and low illumination conditions, which have not been extensively studied until now due to clear challenges. For example, images taken under rainy days are subject to low illumination, while wet roads cause light reflection and distort the appearance of lane and road markings. At night, color distortion occurs under limited illumination. As a result, no benchmark dataset exists and only a few developed algorithms work under poor weather conditions. To address this shortcoming, we build up a lane and road marking benchmark which consists of about 20,000 images with 17 lane and road marking classes under four different scenarios: no rain, rain, heavy rain, and night. We train and evaluate several versions of the proposed multi-task network and validate the importance of each task. The resulting approach, VPGNet, can detect and classify lanes and road markings, and predict a vanishing point with a single forward pass. Experimental results show that our approach achieves high accuracy and robustness under various conditions in realtime (20 fps). The benchmark and the VPGNet model will be publicly available.

With the advent of commodity autonomous mobiles, it is becoming increasingly prevalent to recognize under extreme conditions such as night, erratic illumination conditions. This need has caused the approaches using multi-modal sensors, which could be complementary to each other. The choice for the thermal camera provides a rich source of temperature information, less affected by changing illumination or background clutters. However, existing thermal cameras have a relatively smaller resolution than RGB cameras that has trouble for fully utilizing the information in recognition tasks. To mitigate this, we aim to enhance the low-resolution thermal image according to the extensive analysis of existing approaches. To this end, we introduce Thermal Image Enhancement using Convolutional Neural Network (CNN), called in TEN, which directly learns an end-to-end mapping a single low resolution image to the desired high resolution image. In addition, we examine various image domains to find the best representative of the thermal enhancement. Overall, we propose the first thermal image enhancement method based on CNN guided on RGB data. We provide extensive experiments designed to evaluate the quality of image and the performance of several object recognition tasks such as pedestrian detection, visual odometry, and image registration.

Drivable region detection is challenging since various types of road, occlusion or poor illumination condition have to be considered in a outdoor environment, particularly at night. In the past decade, Many efforts have been made to solve these problems, however, most of the already existing methods are designed for visible light cameras, which are inherently inefficient under low light conditions. In this paper, we present a drivable region detection algorithm designed for thermal-infrared cameras in order to overcome the aforementioned problems. The novelty of the proposed method lies in the utilization of on-line road initialization with a highly scene-adaptive sampling mask. Furthermore, our prior road information extraction is tailored to enforce temporal consistency among a series of images. In this paper, we also propose a large number of experiments in various scenarios (on-road, off-road and cluttered road). A total of about 6000 manually annotated images are made available in our website for the research community. Using this dataset, we compared our method against multiple state-of-the-art approaches including convolutional neural network (CNN) based methods to emphasize the robustness of our approach under challenging situations.

With the increasing interest in pedestrian detection, pedestrian datasets have also been the subject of research in the past decades. However, most existing datasets focus on a color channel, while a thermal channel is helpful for detection even in a dark environment. With this in mind, we propose a multispectral pedestrian dataset which provides well aligned color-thermal image pairs, captured by beam splitter-based special hardware. The color-thermal dataset is as large as previous color-based datasets and provides dense annotations including temporal correspondences. With this dataset, we introduce multispectral ACF, which is an extension of aggregated channel features (ACF) to simultaneously handle color-thermal image pairs. Multi-spectral ACF reduces the average miss rate of ACF by 15%, and achieves another breakthrough in the pedestrian detection task.

We propose a spatially varying stitching method with line correspondences. We are motivated by the observation that point features could be spatially biased or not matched in practice, e.g., repeated textures or homogeneous regions of man-made structures. In this scenario, line matches can provide strong correspondences as well as supplement cues, such as the structure preserving property. With these advantages, we adopt a feature fusion method that combines point and line correspondences into a unified framework for spatially varying stitching. We then estimate the balancing parameter between the point and line terms using geometric error. Our experiments show accurate alignment for challenging but common cases.

As people are becoming interested in paintings, various user-interactive search systems have been presented in recent times. Many systems encourage users to search paintings by prior knowledge on paintings. We discover the limitation for existing methods on how well the query is represented by the user, and propose a simple, yet effective way to search the painting by exploiting the color to express human visual memory. To achieve our goal, we suggest color clustering based on human color perception, and hierarchical metric learning to accommodate the locality of colors. With user-interactive drawing through learned colors, the user completes the abstract image to resemble the visual memory. We show that our system is easy to use, fast to process, accurate to search and fully extensible to cover deviation among users.