Delayed and partially observable state information poses significant challenges for reinforcement learning (RL)-based control in real-world autonomous driving. In highway on-ramp merging, a roadside unit (RSU) can sense nearby traffic, perform edge perception, and transmit state estimates to the ego vehicle over vehicle-to-infrastructure (V2I) links. With recent advancements in intelligent transportation infrastructure and edge computing, such RSU-assisted perception is increasingly realistic and already deployed in modern connected roadway systems. However, edge processing time and wireless transmission can introduce stochastic V2I communication delays, violating the Markov assumption and substantially degrading control performance. In this work, we propose DAROM, aDelay-AwareReinforcementLearning framework forOn-rampMerging that is robust to stochastic delays. We model the problem as a random delay Markov decision process (RDMDP) and develop a unified RL agent for joint longitudinal and lateral control. To recover a Markovian representation under delayed observations, we introduce a Delay-Aware Encoder that conditions on delayed observations, masked action histories, and observed delay magnitude to infer the current latent state. We further integrate a physics-based safety controller to reduce collision risk during merging. Experiments in the simulation of urban mobility (SUMO) simulator using real-world traffic data from the Next Generation Simulation (NGSIM) dataset demonstrate that DAROM consistently outperforms standard RL baselines across traffic densities. In particular, the gated recurrent unit (GRU)-based encoder achieves over 99% success in high-density traffic with random V2I delays of up to 2.0 seconds.

Underwater wireless optical communication (UWOC) is a key technology for supporting information transmission in the Internet of Underwater Things (IoUT). Recently, semantic communication has been introduced into UWOC systems to enhance transmission efficiency and robustness. However, existing underwater wireless optical semantic communication (UWOSC) systems overlook the bandwidth limitation imposed by practical optoelectronic devices, which hinders high-speed semantic information transmission. In this paper, we introduce orthogonal frequency division multiplexing (OFDM) modulation into the UWOSC system for the first time, and design a novel OFDM-based UWOSC system with symbol and power loading (SPL). In the proposed system, shifted-window-based hierarchical vision transformer blocks are employed to extract semantic features and encode them into frequency-domain baseband symbols for OFDM transmission. Furthermore, an SPL scheme, comprising an entropy model-driven symbol reordering strategy and a lightweight power allocation network, is designed to adaptively allocate subcarriers and power based on semantic importance and channel conditions. Experiments conducted on an emulated UWOC platform demonstrate that the proposed OFDM-based UWOSC system achieves superior performance compared with baseline schemes under high transmission bandwidth scenarios. Moreover, the introduction of the SPL module further improves semantic spectrum efficiency, effectively mitigating the adverse impact of low-pass characteristic inherent in bandwidth-limited UWOSC systems. These results demonstrate that the proposed system has strong potential to enable high-speed semantic communication in the IoUT.

We present X2Video, the first diffusion model for rendering photorealistic videos guided by a sequence of intrinsic channels including albedo, normal, roughness, metallicity, and irradiance, while supporting intuitive multi-modal controls with reference images and text prompts for both global and local regions. The intrinsic guidance allows accurate manipulation of color, material, geometry, and lighting, while reference images and text prompts provide intuitive adjustments in the absence of intrinsic information. To enable these functionalities, we extend the intrinsic-guided image generation model XRGB to video generation by employing a novel and efficient Hybrid Self-Attention, which ensures temporal consistency across video frames and also enhances fidelity to reference images. We further develop a Masked Cross-Attention to disentangle global and local text prompts, applying them effectively onto respective local and global regions. For generating long videos, our novel Recursive Sampling method incorporates progressive frame sampling, combining keyframe prediction and frame interpolation to maintain long-range temporal consistency while preventing error accumulation. To support the training of X2Video, we assembled a video dataset named InteriorVideo, featuring 1,154 rooms from 295 interior scenes, complete with reliable ground-truth intrinsic channel sequences and smooth camera trajectories. Both qualitative and quantitative evaluations demonstrate that X2Video can produce long, temporally consistent, and photorealistic videos guided by intrinsic conditions. Additionally, X2Video effectively accommodates multi-modal controls with reference images, global and local text prompts, and simultaneously supports editing on color, material, geometry, and lighting through parametric tuning. Upon acceptance, we will publicly release our model and dataset.

Recently, underwater wireless optical communication (UWOC) has emerged to support the high data rate requirements of oceanic exploration. In this paper, we propose an accurate and closed-form UWOC channel model to understand the effects of dynamic ocean environment on optical signal propagation. The model takes into account the impairments induced by oceanic path-loss, oceanic turbulence, pointing error loss and link interruption due to angle-of-arrival (AoA) fluctuations jointly. We further derive analytical expressions for various outage performance metrics. To boost the system robustness to dynamic ocean environment, we design a probabilistic shaping (PS)-based strategy with unipolar pulse amplitude modulation (PAM), which maximizes the ergodic constellation constrained capacity. Furthermore, considering the limitation of computational resources in real ocean environment, we simplify the PS-based scheme to alleviate the problem. Numerical results verify the accuracy of the proposed channel model and the outage performance analysis. Moreover, the simplified PS-based unipolar M-PAM scheme is validated to be a promising solution for the development and deployment of high speed adaptive UWOC systems.

Perceiving the environment is one of the most fundamental keys to enabling Cooperative Driving Automation, which is regarded as the revolutionary solution to addressing the safety, mobility, and sustainability issues of contemporary transportation systems. Although an unprecedented evolution is now happening in the area of computer vision for object perception, state-of-the-art perception methods are still struggling with sophisticated real-world traffic environments due to the inevitable physical occlusion and limited receptive field of single-vehicle systems. Based on multiple spatially separated perception nodes, Cooperative Perception (CP) is born to unlock the bottleneck of perception for driving automation. In this paper, we comprehensively review and analyze the research progress on CP, and we propose a unified CP framework. The architectures and taxonomy of CP systems based on different types of sensors are reviewed to show a high-level description of the workflow and different structures for CP systems. The node structure, sensing modality, and fusion schemes are reviewed and analyzed with detailed explanations for CP. A Hierarchical Cooperative Perception (HCP) framework is proposed, followed by a review of existing open-source tools that support CP development. The discussion highlights the current opportunities, open challenges, and anticipated future trends.

We propose the first video diffusion framework for reference-based lineart video colorization. Unlike previous works that rely solely on image generative models to colorize lineart frame by frame, our approach leverages a large-scale pretrained video diffusion model to generate colorized animation videos. This approach leads to more temporally consistent results and is better equipped to handle large motions. Firstly, we introduce Sketch-guided ControlNet which provides additional control to finetune an image-to-video diffusion model for controllable video synthesis, enabling the generation of animation videos conditioned on lineart. We then propose Reference Attention to facilitate the transfer of colors from the reference frame to other frames containing fast and expansive motions. Finally, we present a novel scheme for sequential sampling, incorporating the Overlapped Blending Module and Prev-Reference Attention , to extend the video diffusion model beyond its original fixed-length limitation for long video colorization. Both qualitative and quantitative results demonstrate that our method significantly outperforms state-of-the-art techniques in terms of frame and video quality, as well as temporal consistency. Moreover, our method is capable of generating high-quality, long temporal-consistent animation videos with large motions, which is not achievable in previous works. Our code and model are available at https://luckyhzt.github.io/lvcd.

Abstract Recent advancements in large‐scale text‐to‐image diffusion models have enabled many applications in image editing. However, none of these methods have been able to edit the layout of single existing images. To address this gap, we propose the first framework for layout editing of a single image while preserving its visual properties, thus allowing for continuous editing on a single image. Our approach is achieved through two key modules. First, to preserve the characteristics of multiple objects within an image, we disentangle the concepts of different objects and embed them into separate textual tokens using a novel method called masked textual inversion. Next, we propose a training‐free optimization method to perform layout control for a pre‐trained diffusion model, which allows us to regenerate images with learned concepts and align them with user‐specified layouts. As the first framework to edit the layout of existing images, we demonstrate that our method is effective and outperforms other baselines that were modified to support this task. Code is available at our project page.

The purpose of this study is to define an operational concept involving connected automated vehicle (CAV) operation on freeway managed lanes. Despite the low projected market penetration of CAVs during the next decade, the use of managed lane facilities has the potential to support the realization of increased mobility benefits by their very nature. The proposed CAV operation involves platoons of equipped vehicles governed by integrated CAV applications, including cooperative adaptive cruise control (CACC), cooperative merge, and speed harmonization. This study proposes an algorithm for integrating CAV applications. Through microscopic simulation, the study particularly examines the effectiveness of CACC, CACC plus cooperative merge, and the addition of speed harmonization under different penetration rates. Simulation results show the effectiveness of the bundled application to enhance system throughput and reduce delay, even with low CAV penetration rates. The speed harmonization shows the greatest effects on delay reduction at medium-to-high penetration rates and some benefits even at low penetration rates. The conclusions provide operational insights and guidance for traffic management centers to implement CAV-based traffic control in the future.

We propose the first unified framework UniColor to support colorization in multiple modalities, including both unconditional and conditional ones, such as stroke, exemplar, text, and even a mix of them. Rather than learning a separate model for each type of condition, we introduce a two-stage colorization framework for incorporating various conditions into a single model. In the first stage, multi-modal conditions are converted into a common representation of hint points. Particularly, we propose a novel CLIP-based method to convert the text to hint points. In the second stage, we propose a Transformer-based network composed of Chroma-VQGAN and Hybrid-Transformer to generate diverse and high-quality colorization results conditioned on hint points. Both qualitative and quantitative comparisons demonstrate that our method outperforms state-of-the-art methods in every control modality and further enables multi-modal colorization that was not feasible before. Moreover, we design an interactive interface showing the effectiveness of our unified framework in practical usage, including automatic colorization, hybrid-control colorization, local recolorization, and iterative color editing. Our code and models are available at https://luckyhzt.github.io/unicolor .

Identity-preserved face beauty transformation aims to change the beauty scale of a face image while preserving the identity of the original face. In our framework of conditional Generative Adversarial Networks (cGANs), the synthesized face produced by the generator would have the same beauty scale indicated by the input condition. Unlike the discrete class labels used in most cGANs, the condition of target beauty scale in our framework is given by a continuous real-valued beauty score in the range [1 to 5], which makes the work challenging. To tackle the problem, we have implemented a triple structure, in which the conditional discriminator is divided into a normal discriminator and a separate face beauty predictor. We have also developed another new structure called Conditioned Instance Normalization to replace the original concatenation used in cGANs, which makes the combination of the input image and condition more effective. Furthermore, Self-Consistency Loss is introduced as a new parameter to improve the stability of training and quality of the generated image. In the end, the objectives of beauty transformation and identity preservation are evaluated by the pretrained face beauty predictor and state-of-the-art face recognition network. The result is encouraging and it also shows that certain facial features could be synthesized by the generator according to the target beauty scale, while preserving the original identity.

DSRC and C-V2X are two fundamentally different communication technologies for connected and automated vehicles (CAVs). This is a rare study aimed at conducting comparative testing between C-V2X and DSRC to help CAV deployer/researchers identify which communication technology is most suitable for their needs. Initial baseline tests between C-V2X and DSRC were performed at a research facility and relevant results from this comparative testing are presented in this paper. The results presented in this paper provide insight into metrics of interest such as packet loss, burst packet loss, and reliability. The authors document the test system and procedures and present the results as observed in the tests.

In this letter, we propose a novel discriminative bag-of-words (DBoW) model that can both adapt to appearance variations over time and reduce the commonly observed drifting problem in online tracking. Specifically, a contextual region containing both the object and its surroundings is explored to construct a compact representation with two bags-of-words. Each visual word is learned to carry discriminative appearance cues for the object. In order to alleviate the drifting problem, an adaptive updating approach is introduced to prevent the integration of the background into the object model. Based on DBoW model, a robust and near real-time tracker is proposed, where tracking is accomplished by searching the candidate that best matches to the maintained DBoW model. Extensive experimental results demonstrate competitive performance of the proposed method to state-of-the-art algorithms.

In this paper, we propose a fast single image dehazing algorithm using domain transformation-based edge-preserving filter and weighed quadtree subdivision. The proposed algorithm first estimates the atmospheric light in the minimal component of the haze image based on the weighed quadtree subdivision. Since the dark channel prior is invalid when the scene objects are with similar intensity to the atmospheric light, we then modify the transmission map to improve the adaptability of the algorithm. Due to the observation that haze is widely spread in the hazy image, the transmission map should be smoothly changed over the scene. The proposed algorithm utilizes the domain transformation-based edge-preserving filter to smooth the details and preserve edges and corners, aiming to obtain the refined transmission map. Experimental results demonstrate that the proposed algorithm produces comparative or even better results compared to the state-of-the-art methods but with much higher computational efficiency.

Due to the presence of bad weather conditions, images captured in outdoor environments are usually degraded. In this paper, a novel single image dehazing method is proposed to enhance the visibility of such degraded images. Since the property of haze is widely spread, the estimated transmission should be smoothly changed over the scene. The fast wavelet transform (FWT) is introduced to estimate the smooth transmission in our work. To preserve more details and correct the color distortion, a solution based on weighted image fusion strategy is provided. Compared with the state-of-the-art single image dehazing methods, our method based on FWT with weighted image fusion (FWTWIF) produces similar or even better results with lower complexity. In order to verify the high visibility restoration and efficiency of our method, comparative experiments are conducted at the end of this paper.

For the color fadedness and the contrast reduction of hazy images, we propose a novel method based on digital total variation (TV) filter with color transfer (DTVFCT) for single color image dehazing. The estimation of atmospheric veil is a filtering problem on the minimal component image and the digital TV filter is applied to preserve the edges and gradients of images to avoid halo artifacts. To obtain a quality vision of a resulting image, color transfer is utilized to protect the final haze-free image's color from high dynamic. The proposed method enjoys a celerity because of fast convergence of digital TV filter. The experiment results show the vivid color and the accuracy of the restored edges and gradients in the comparative study.

Visual tracking under illumination changes is a challenging task for various computer vision systems. In this paper, we propose a robust and efficient tracking algorithm based on a novel feature descriptor called joint gradient-intensity histogram, which exploits both the pixel intensity and gradient orientation features. Unlike the traditional histogram based algorithms, the joint gradient-intensity histogram is extracted efficiently by employing the integral histogram, which is calculated recursively in the specially designed local image region, making the exhaustively searching process in real time. Experiments with the state-of-art tracking methods demonstrate superior performance of the proposed tracking algorithm under illumination changes.

In this letter, we propose a robust and real-time visual tracking algorithm via a novel kernel based multiple cue adaptive appearance model (KBMCAAM). In particular, the appearance model is constructed with a naive Bayes classifier which is trained utilizing sparse multi-scale Haar-like features weighted by a spatial kernel function. Moreover, multiple image cues are integrated to improve the model's discriminative capacity. Experimental results demonstrate the superior performance of our proposed method to many state-of-art algorithms.

This paper studies the robust speech recognition based on auditory model. The spectrum of auditory representation shows that the lateral inhibition network (LIN) can shape the spatial input patterns and highlight their edges and peaks. Also, it can make the speech recognition to be more robust to noise than the LPC cepstral (LPC-CEP) approach. Some preliminary experiments including speaker dependent and speaker independent recognition were performed using both the model and LPC-CEP respectively. A set of 405 Chinese mandarin syllables was taken as the reference. The results of the experiment show that the recognition ratio based on the auditory model was equal to that of LPC-CEP in the case of non-noise. However, the recognition ratio based on the auditory model was much higher under the white noise of about 2.8 dB. Both theoretical and experimental studies show that the auditory model not only represents speech signal well but is also robust.

Describes a characteristic of Chinese speech, according to the duration time of Chinese consonant, and a recognition algorithm without end-point detection is proposed. Three situations in this algorithm have been pointed out, but the same result has been obtained from them. Compared with the traditional method, in this algorithm, it is not necessary to decide the end-point of speech signals. From the beginning, feature vectors, which consist of 15-order cepstrum coefficients and the average energy of each frame, are extracted in frames (length of each frame is 20 millisecond, the overlapping between two frames is 50%). By introducing the self-loop of the silent segment of the discrete time warping (DTW) and HMM unified model (DHUM), this algorithm is successfully implemented. In recognition of 99 similar words of Chinese, a first candidate recognition rate of 94.95% is obtained. To study the robustness of the algorithm, auditory representation of speech signals is also employed to obtained feature vectors. From the comparison of different feature-extraction methods, the conclusion is obtained that if an auditory feature is accepted for feature vectors, the robustness of the algorithm will be better; and because of the superiority of auditory representation to describe the characteristics of the silent segment of speech, the auditory feature-vector is more suitable for this algorithm.