Vision Foundation Models(VFMs) have achieved remarkable success in various computer vision tasks.However, their application to semantic segmentation is hindered by two significant challenges: (1) the disparity in data scale, as segmentation datasets are typically much smaller than those used for VFM pre-training, and (2) domain distribution shifts, where real-world segmentation scenarios are diverse and often underrepresented during pre-training. To overcome these limitations, we present Rein++, an efficient VFM-based segmentation framework that demonstrates superior generalization from limited data and enables effective adaptation to diverse unlabeled scenarios. Specifically, Rein++ comprises a domain generalization solution Rein-G and a domain adaptation solution Rein-A. Rein-G introduces a set of trainable, instance-aware tokens that effectively refine the VFM's features for the segmentation task. This parameter-efficient approach fine-tunes less than 1% of the backbone's parameters, enabling robust generalization. Building on the Rein-G, Rein-A performs unsupervised domain adaptation at both the instance and logit levels to mitigate domain shifts. In addition, it incorporates a semantic transfer module that leverages the class-agnostic capabilities of the segment anything model to enhance boundary details in the target domain. The integrated Rein++ pipeline first learns a generalizable model on a source domain (e.g., daytime scenes) and subsequently adapts it to diverse target domains (e.g., nighttime scenes) without any target labels. Comprehensive experiments demonstrate that Rein++ significantly outperforms state-of-the-art methods with efficient training, underscoring its roles an efficient, generalizable, and adaptive segmentation solution for VFMs, even for large models with billions of parameters.

The reliability of vision-based systems, such as traffic monitoring and intelligent driving, is typically compromised in hazy weather owing to diminished visibility. In this paper, we propose a novel efficient image dehazing framework guided by depth order, leveraging the consistency of depth perception to establish strong global constraints for enhanced haze removal. The consistent depth perception ensures that the regions that look farther or closer in hazy images also appear farther or closer in the corresponding dehazing results, substantially avoiding potential visual degradation. To this end, the depth order in hazy images is approximated by the reverse order of color difference between pixel values and global atmospheric light, offering an effective and efficient alternative for depth perception modeling. Subsequently, we have developed a depth order embedded transformation model to estimate the transmission maps jointly constrained by depth order and haze imaging model, ensuring that the depth order remains unchanged in corresponding dehazing results. This model harnesses the extracted depth order as a powerful global constraint for the dehazing process, facilitating the efficient use of global information and thus achieving superior image restoration. Extensive experiments demonstrate that the proposed method can better recover potential structure and vivid color with higher computational efficiency, offering an efficient solution for robust traffic monitoring against hazy weather.

To serve the intricate and varied demands of image editing, precise and flexible manipulation in image content is indispensable. Recently, Drag-based editing methods have gained impressive performance. However, these methods predominantly center on point dragging, resulting in two noteworthy drawbacks, namely “miss tracking ”, where dif-ficulties arise in accurately tracking the predetermined han-dle points, and “ambiguous tracking”, where tracked points are potentially positioned in wrong regions that closely re-semble the handle points. To address the above issues, we propose FreeDrag, a feature dragging methodology designed to free the burden on point tracking. The Free-Drag incorporates two key designs, i.e., template feature via adaptive updating and line search with backtracking, the former improves the stability against drastic content change by elaborately controlling the feature updating scale after each dragging, while the latter alleviates the misguidance from similar points by actively restricting the search area in a line. These two technologies together contribute to a more stable semantic dragging with higher efficiency. Comprehensive experimental results substantiate that our approach significantly outperforms pre-existing methodologies, offering reliable point-based editing even in various complex scenarios.

In this paper, we first assess and harness various Vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely “Rein”, to parameter-efficiently harness VFMs for DGSS. Built upon a set of trainable tokens, each linked to distinct instances, Rein precisely refines and forwards the feature maps from each layer to the next layer within the backbone. This process produces diverse refinements for different categories within a single image. With fewer trainable parameters, Rein efficiently fine-tunes VFMs for DGSS tasks, surprisingly surpassing full parameter fine-tuning. Extensive experiments across various settings demonstrate that Rein significantly outperforms state-of-the-art methods. Remarkably, with just an extra 1% of trainable parameters within the frozen backbone, Rein achieves a mIoU of 78.4% on the Cityscapes, without accessing any real urban-scene datasets. Code is available at https://github.com/w1oves/Rein.git.

Structured pruning is an efficient compression technique that significantly reduces the inference latency and energy consumption of convolutional neural networks (CNNs) by eliminating redundant filters. However, existing works suffer from expensive algorithm costs in multi-hardware deployment scenarios involving several budgets across multiple hardware devices. To tackle this challenge, we propose a novel all-in-one hardware-oriented compression framework (AHC), which integrates structured pruning and data pruning to rapidly generate vast hardware-efficient models with ultra-low pruning and fine-tuning costs. Specifically, AHC develops a unified hardware-aware pruning (UHP), which rapidly generates numerous hardware-efficient models for several budgets across multiple hardware devices in once pruning process, thereby reducing pruning costs in multi-hardware deployment scenarios. Moreover, AHC proposes a progressive data pruning (PDP), which gradually removes samples that have a negligible impact on enhancing the predictive ability of pruned models, thereby accelerating the fine-tuning process with negligible performance loss. Extensive experiments demonstrate the superiority of the AHC over state-of-the-art (SOTA) structured pruning methods in terms of algorithm costs, latency, and accuracy. In particular, compared with SOTA hardware-oriented pruning method, AHC achieves comparable performances while reducing$5.3\times $pruning costs and$2.7\times $fine-tuning costs in multi-hardware deployment scenarios. Code is available athttps://github.com/HXuan-Wang/AHC.

A mirror-like surface (MLS) reflects highlight, aggravating the image saturation in structured light 3-D reconstruction systems and precluding defect detection based on reconstructed 3-D profiles. Previous studies have focused on a strategy of limiting the luminous flux entering the camera. However, the high intensity of the reflected highlight forces the limitation to be strengthened, which heavily reduces the modulation in the images for the 3-D reconstruction. Therefore, we propose a new strategy to adjust the source of the reflected highlight, i.e., the bidirectional reflectance (BR) of the MLS, which fundamentally suppresses the highlight and removes the limitation on the luminous flux. To execute the proposed strategy, an unfixed view structured light system (UVSLS) is established. The UVSLS converts the reflection viewer from the real camera to the virtual camera, realizing the flexible adjustment of the MLS BR. Finally, an MLS 3-D reconstruction framework is constructed to obtain the 3-D profile of the MLS. Experiments demonstrate that the proposed framework reduces the saturated pixels by 73.72% compared with the conventional method. Compared with the previous methods, the saturated pixels are reduced by an average of 47.62%.

Recently, learning-based multi-exposure fusion (MEF) methods have made significant improvements. However, these methods mainly focus on static scenes and are prone to generate ghosting artifacts when tackling a more common scenario, i.e., the input images include motion, due to the lack of a benchmark dataset and solution for dynamic scenes. In this paper, we fill this gap by creating an MEF dataset of dynamic scenes, which contains multi-exposure image sequences and their corresponding high-quality reference images. To construct such a dataset, we propose a 'static-for-dynamic' strategy to obtain multi-exposure sequences with motions and their corresponding reference images. To the best of our knowledge, this is the first MEF dataset of dynamic scenes. Correspondingly, we propose a deep dynamic MEF (DDMEF) framework to reconstruct a ghost-free high-quality image from only two differently exposed images of a dynamic scene. DDMEF is achieved through two steps: pre-enhancement-based alignment and privilege-information-guided fusion. The former pre-enhances the input images before alignment, which helps to address the misalignments caused by the significant exposure difference. The latter introduces a privilege distillation scheme with an information attention transfer loss, which effectively improves the deghosting ability of the fusion network. Extensive qualitative and quantitative experimental results show that the proposed method outperforms state-of-the-art dynamic MEF methods. The source code and dataset are released at https://github.com/Tx000/Deep_dynamicMEF.

Bevel-tip steerable needles are widely used in modern minimally invasive percutaneous procedures to reach specific positions inside the body. In this paper, we propose a dynamic path planning approach to insert a steerable needle into soft tissue. Based on mathematic modeling of soft tissue deformation during the insertion process, the proposed approach can drive the needle to reach a goal position in deformable environment. As the goal position changes in the deformable environment, a dynamic path planner is proposed to re-plan the path until the needle tip approaches the target successfully. Simulation and experiment are performed to demonstrate the effectiveness of the proposed approach to insert a flexible needle in deformable environment.

In this paper we introduce a new rule for butterfly subdivision scheme which overcome a shortcoming with the sharp features. For butterfly subdivision scheme, many features will be lost after several times of refinement. This new rule solved this problem by removing the position of new interpolated vertices. And our method can also implement in some other subdivision schemes.

A new 3D platform is build in the self developed WebCAD system, used for multiple user collaborative design. As an extension of the WebCAD system, the collaborative 3D CAD system proposes a collaborative Boolean operation method. With the method complex physical objects can be easily obtained through Boolean operations of some elemental entities. With the new system, geographically distributed designers can design and edit 3D entities collaboratively on their own browsers. A three-tier architecture and an entity-based access control mechanism to settle confliction in collaborative design process are also employed in the system.

A web-based collaborative design platform is presented for design MEMS structure. The design platform consists of four parts: mask design and optimization, lithography simulation, 3D reconstruction and synchronous display. Some special technologies in constructing the platform are described. An entity- based access control mechanism is employed to settle confliction in collaborative design process; MC algorithm is used to reconstruct 3D entities. A method is proposed to make up for the shortfall of MC to cover the holes in forming 3D surface. Application of the research will shorten the production cycle of MEMS and access higher accuracy significantly.

A Web-based synchronous collaborative environment is presented, which facilitates the education of mechanical engineering design. With the system, participants at different physical locations gather online to discuss topics of interest. Members of the group can directly manipulate all entities in the engineering draft interactively on their browsers and updated results show on the partners' web pages synchronously. An entity-based access control mechanism resolves conflicts and maintains consistency of design data, so participants can co-operate efficiently. The system provides benefits for teachers as well as students. It runs in a self-developed Web-based CAD software environment.

In order to create a platform for customer oriented Web-based virtual design, an interactive and collaborative discussing environment for both customers and enterprise designers is necessary. In the system, VRML model of the products is employed as the intermedium of the communication. An approach to reconstruct VRML model is presented. The manner makes VRML model be operable interactively and displayed online synchronously. The method of pretreatment of VRML model and the relevant key technologies are proposed and realized

Market competition is forcing companies to develop and manufacture diverse products to meet customer's requirements. It is very important to respond to the market quickly in design. In this paper, a Web-based virtual design environment is presented, which allows customers to participate in product design directly and help designers to adjust the structure of their products conveniently. In the proposed system, product family models are constructed and a special feature language is defined. A product configurator is designed and the product configuration process is also accomplished. A collaborative environment, which is used for customers and engineers to discuss with each other, is also introduced. The cooperative design of an instrumental cabinet is introduced as an implementation, which has proved the feasibility of the system.