46 accepted papers
Model merging integrates multiple task-specific models into a single consolidated one. Recent research has made progress in improving merging performance for in-distribution or multi-task scenarios, but domain generalization in model merging remains underexplored. We investigate how merging models f
Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalignment between isotropic objectives and the intrinsic natural image manifold. While Direct Preference Optimization offers a path to alignment, its reli…
How does the choice of optimization algorithm shape a model’s ability to learn features? To address this question for steepest descent methods—including sign descent, which is closely related to Adam—we introduce steepest mirror flows as a unifying theoretical framework. This framework reveals how o…
Passive electric sense, a unique underwater perception ability in aquatic species, enables fish to detect external electrical signals and perform essential life activities in dark or turbid environments. Inspired by the passive electrosensing capability of natural shark, this letter proposes a low-c
Classical video quality assessment (VQA) methods generate a numerical score to judge a video's perceived visual fidelity and clarity. Yet, a score fails to describe the video's complex quality dimensions (e.g., noise), restricting its applicability. Benefiting from the human-friendly linguistic outp
Look-Up Table based methods have emerged as a promising direction for efficient image restoration tasks. Recent LUT-based methods focus on improving their performance by expanding the receptive field. However, they inevitably introduce extra computational and storage overhead, which hinders their de
Diffusion models have gained attention for their success in modeling complex distributions, achieving impressive perceptual quality in SR tasks. However, existing diffusion-based SR methods often suffer from high computational costs, requiring numerous iterative steps for training and inference. Exi
Video Quality Assessment (VQA), which intends to predict the perceptual quality of videos, has attracted increasing attention. Due to factors like motion blur or specific distortions, the quality of different regions in a video varies. Recognizing the region-wise local quality within a video is bene…
Implicit bias plays an important role in explaining how overparameterized models generalize well. Explicit regularization like weight decay is often employed in addition to prevent overfitting. While both concepts have been studied separately, in practice, they often act in tandem. Understanding the…
Neural video compression (NVC) has made significant progress in recent years, while neural B-frame video compression (NBVC) remains underexplored compared to P-frame compression. NBVC can adopt bi-directional reference frames for better compression performance. However, NBVC's hierarchical coding ma…
Finetuning large pretrained neural networks is known to be resource-intensive, both in terms of memory and computational cost. To mitigate this, a common approach is to restrict training to a subset of the model parameters. By analyzing the relationship between gradients and weights during finetunin…
High-resolution (HR) images are commonly downscaled to low-resolution (LR) to reduce bandwidth, followed by upscaling to restore their original details. Recent advancements in image rescaling algorithms have employed invertible neural networks (INNs) to create a unified framework for downscaling and…
Fish actively control their bodies to interact with the surrounding vortex flow field and generate thrust. Current research on the propulsion mechanisms of robotic fish primarily involves qualitative comparisons of vortex structures from simulations and experiments, lacking quantitative analysis. Th
Personality assessment is essential for developing user-centered systems, playing a critical role across domains including hiring, education, and personalized system design. With the integration of conversational AI systems into daily life, automatically assessing human personality through natural l
Recent advancements in unified image generation models, such as OmniGen, have enabled the handling of diverse image generation and editing tasks within a single framework, accepting multimodal, interleaved texts and images in free form. This unified architecture eliminates the need for text encoders…
The performance gap between training sparse neural networks from scratch (PaI) and dense-to-sparse training presents a major roadblock for efficient deep learning. According to the Lottery Ticket Hypothesis, PaI hinges on finding a problem specific parameter initialization. As we show, to this end,…
Existing multimodal large model-based image compression frameworks often rely on a fragmented integration of semantic retrieval, latent compression, and generative models, resulting in suboptimal performance in both reconstruction fidelity and coding efficiency. To address these challenges, we propo…
Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also posed limitations on their application. Building upon the tr…
"Recent Blind Image Super-Resolution (BSR) methods have shown proficiency in general images. However, we find that the efficacy of recent methods obviously diminishes when employed on image data with blur, while image data with intentional blur constitute a substantial proportion of general data. To…
Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches primarily focus on fixed upsampling ratios, disregarding the fact that the effective bandwidth of captured audio may fluctuat…
Recently numerous approaches have achieved notable success in compressed video quality enhancement (VQE). However these methods usually ignore the utilization of valuable coding priors inherently embedded in compressed videos such as motion vectors and residual frames which carry abundant temporal a…
Short-form UGC video platforms like Kwai and TikTok have been an emerging and irreplaceable mainstream media form thriving on user-friendly engagement and kaleidoscope creation etc. However the advancing content generation modes e.g. special effects and sophisticated processing workflows e.g. de-art…
"Deep learning-based methods have shown remarkable performance in single JPEG artifacts removal task. However, existing methods tend to degrade on double JPEG images, which are prevalent in real-world scenarios. To address this issue, we propose Offset-Aware Partition Transformer for double JPEG art…
Video quality assessment (VQA) is a challenging problem due to the numerous factors that can affect the perceptual quality of a video e.g. content attractiveness distortion type motion pattern and level. However annotating the Mean opinion score (MOS) for videos is expensive and time-consuming which…
"Diffusion-based methods, endowed with a formidable generative prior, have received increasing attention in Image Super-Resolution (ISR) recently. However, as low-resolution (LR) images often undergo severe degradation, it is challenging for ISR models to perceive the semantic and degradation inform…
Video compressive sensing (VCS) presents a promising encoder paradigm for efficient video signals acquisition at resource-limited applications. In order to recover complete and accurate signals at the decoder, powerful reconstruction algorithms are desired to exploit rich temporal redundancies withi…
The high speed and low energy cost are two conflicting objectives in the motion optimization of bio-inspired underwater robots, but playing a very important role. To this end, this paper proposes an optimization strategy for swimming speed and power cost using an improved NSGA-II for a flexible robo…
The development of biomimetics and the demand for higher propulsion efficiency lead to more research in helical propulsion robots. This letter presents a novel sperm-inspired robot that utilizes flexible tail as propulsion and analyzes the motion performance. Firstly, the robot's propulsion system i
A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling capability, they fail to properly balance the accuracy and effic…
To date, untethered micro/nanorobots have attracted considerable attention in various aspects due to their unique potential for in-vivo applications such as the targeted therapy. One of the most promising types of micro/nanorobots is the class of ferromagnetic microrobots which can be efficiently ac…
In this paper, we propose a novel network structure to solve the blind hyperspectral unmixing problem using a double Deep Image Prior (DIP). In particular, the blind unmixing problem involves two sub-problems: endmember estimation and abundance estimation. We, therefore, propose two sub-networks, en…
The integral flexible tail has the potential advantage of lifelike undulating motion. However, due to the complex manufacturing process and difficult modification of structural parameters, its application in robotic fish encounters many challenges. Combining rigid structure and flexible material, th
The complex and continuous undulation of fishtail facilitates extraordinary underwater motion performance for natural fish. For the widely used Multi-Joint robotic fish, a lot of joints are used to simulate continuum fishtail, resulting in some challenges, e.g., the mechanism complexity, friction lo
Sub-structures such as micro-structured magnetic teeth fabricated with an artificial bacteria flagellum (ABF) are designed for achieving more motion modes, higher precision, and better controllability. To achieve these, a more precise model considering the non-circular cross-sectional features is se…
To date, untethered microrobots have been receiving tremendous attention for playing implacable roles of maneuverable tools in fields such as microfabrication and biomanipulation. Typical actuation of such untethered tiny robots is the magnetic field-based approaches, including gradient and rotation…
In this paper, we use algorithm unrolling approaches in order to design a new neural network structure applicable to hyperspectral unmixing challenges. In particular, building upon a constrained sparse regression formulation of the underlying unmixing problem, we unroll an ADMM solver onto a neural…
We consider compressive sensing problems with model mismatch where one wishes to recover a sparse high-dimensional vector from low-dimensional observations subject to uncertainty in the measurement operator. In particular, we design a new robust deep neural network architecture by applying algorithm…
Among visual relocalization from a single RGB image, the scene coordinate regression (SCoRe) based on convolutional neural network (CNN) becomes prevailing, however, it is insufficient to extract invariant features under different viewpoints due to fixed geometric structures of CNN. In this letter,
We address the problem of detecting scene text in arbitrary shapes, which is a challenging task due to the high variety and complexity of the scene. Specifically, we treat text detection as instance segmentation and propose a segmentation-based framework, which extracts each text instance as an inde…
Cell morphology plays an important role in maintaining normal cellular functions. Existing techniques for cell morphology measurement, such as confocal imaging and atomic force microscopy, have the limitations of photobleaching and incompatibility for integration with other cell manipulation instrum
In this paper, we design and build a power line inspection robot capable of hybrid operation modes. Specifically, the developed robot is able to land on the overhead ground wire (OGW) and to move as the climbing robot. When to negotiate obstacles, it can vertically take off the wire and fly over the…
Estimating correspondence between two images and extracting the foreground object are two challenges in computer vision. With dual-lens smart phones, such as iPhone 7Plus and Huawei P9, coming into the market, two images of slightly different views provide us new information to unify the two topics.…
Embryo vitrification is an essential cryopreservation technique in IVF (in vitro fertilization) clinics. Vitrification involves pick-and-place of an embryo in multiple types of cryoprotectant solutions for processing before placing the embryo on a vitrification straw for cryopreservation in liquid n
In recent years, convolutional neural networks have shown its strong power for stereo matching cost learning. Current approaches learn the parameters of their models from public datasets with ground truth disparity. However, due to the limitations of these datasets and the difficulty of collecting n…
In this paper, we study an unconventional but practically meaningful reversibility problem of commonly used image filters. We broadly define filters as operations to smooth images or to produce layers via global or local algorithms. And we raise the intriguingly problem if they are reservable to the…
Previous joint/guided filters directly transfer the structural information in the reference image to the target one. In this paper, we first analyze its major drawback -- that is, there may be completely different edges in the two images. Simply passing all patterns to the target could introduce sig…