We introduce the Hybrid Vector-Occupancy Field (HVOF), a new implicit 3D representation for reconstructing both open and closed surfaces from sparse point clouds. Existing approaches, such as occupancy field and signed distance fields, face severe limitations. They struggle with open surfaces, while unsigned distance field and neural vector field exhibit directional instability in complex topologies and ridge regions. HVOF addresses these challenges by incorporating a smoothly decaying occupancy field around the surface, while capturing precise local geometry using truncated displacement vectors, naturally mitigating direction-field ambiguities near ridge regions. This unified design forms a robust hybrid representation that leverages both occupancy and vector fields. To fulfill it, we design a Hybrid Field variational autoencoder including a hierarchical cross-attention encoder and dual-branch decoder that jointly learn occupancy and vector fields through continuous weighting. Extensive experiments demonstrate that HVOF consistently outperforms state-of-the-art methods across ShapeNet, ABC, and MGN datasets, accurately reconstructing both open and closed surfaces while preserving fine geometric details in complex regions.

Human Novel View Synthesis (HNVS) aims to synthesize photorealistic human images from novel viewpoints given observations from known views. Despite significant advances achieved by existing methods such as NeRF, diffusion models, and 3DGS, they still face substantial challenges in achieving stable modeling from a single image. In this paper, we introduce Dual-Constraint Human Gaussian Splatting (DcSplat), a novel, simple, and efficient 3D Gaussian-based framework for single-view 3D human reconstruction. To address occlusion-induced texture missing and depth ambiguities, we introduce two key components: a Latent Multi-View Consistency Constraint Mechanism and a Geometric Constraint Module. The former employs a Latent-space Appearance Transformer (LatentFormer) to learn semantically coherent, view-consistent appearance priors via SMPL-guided pseudo-view fusion. The latter refines noisy SMPL-based depth through a U-Net-like structure conditioned on latent appearance features. These two modules are jointly optimized to generate high-quality Gaussian parameters in a unified latent space. Extensive experiments demonstrate that DcSplat outperforms existing SOTA methods in both geometry and texture quality, while achieving fast inference and lower computational cost.

Human pose generation is a complex task due to the non-rigid and highly variable nature of human body structures and appearances. However, existing methods often overlook the fundamental differences between spatial transformations of poses and texture generation for appearance, which makes them prone to overfitting. To address this issue, we propose a multi-pose generation framework driven by disentangled pose and appearance guidance. Our approach includes a Global-aware Pose Generation module that iteratively generates pose embeddings, enabling effective control over non-rigid body deformations. Additionally, we introduce the Global-aware Transformer Decoder, which leverages similarity queries and attention mechanisms to achieve spatial transformations and enhance pose consistency through a Global-aware block. In the appearance generation phase, we condition a diffusion model on pose embeddings produced in the initial stage and introduce an Appearance Adapter that extracts high-level contextual semantic information from multi-scale features, enabling further refinement of pose appearance textures and providing appearance guidance. Extensive experiments on the UBC Fashion and TikTok datasets demonstrate that our framework achieves state-of-the-art results in both quality and fidelity, establishing it as a powerful approach for complex pose generation tasks.

Pose diversity is an inherent representative characteristic of 2D images. Due to the 3D to 2D projection mechanism, there is evident content discrepancy among distinct pose images. This is the main obstacle bothering pose transformation related researches. To deal with this challenge, we propose a fine-grained incremental evolution centered pose generation framework, rather than traditional direct one-to-one in a rush. Since proposed approach actually bypasses the theoretical difficulty of directly modeling dramatic non-linear variation, the incurred content distortion and blurring could be effectively constrained, at the same time the various individual pose details, especially clothes texture, could be precisely maintained. In order to systematically guide the evolution course, both global and incremental evolution constraints are elaborately designed and merged into the overall framework. And a novel triple-path knowledge fusion structure is worked out to take full advantage of all available valuable knowledge to conduct high-quality pose synthesis. In addition, our framework could generate a series of valuable by-products, namely the various intermediate poses. Extensive experiments have been conducted to verify the effectiveness of the proposed approach. Code is available at https://github.com/Xiaofei-CN/Incremental-Evolution-Pose-Generation.

Object detection from remote sensing images is an interesting research topic full of theoretical and application values. Compared with generic images, those of remote sensing contain much less distinguishing representation information due to far-away capturing position and limited camera lens resolution, the perpendicular to ground capturing view, almost unacquirable 3-D object structure and serious roof occlusion, and the inherent unimportance of top roof view. Focusing on this intrinsic disadvantage, in this letter, we propose a general framework of accurate remote sensing object localization constructed with the core idea of maximum image feature exploration. This integrated structure is mainly comprised of cascaded tiny patch correlation (CTPC) based feature digging, averaging local patch regression (ALPR) centered coarse location acquisition, and instance segmentation oriented further refinement (ISOFR). All those components are designed to maximize feature digging and usage. We believe this is the first to implement the idea of maximum feature exploration to each corner of object detection architecture. Extensive experiments on challenging aerial image datasets DOTA and NWPU VHR-10 show state-of-the-art performance.

Aiming to obtain more discriminative features in scene images and overcome the impacts of intra-class differences and inter-class similarities, the paper proposes a scene recognition method that combines attention and context information. First, we introduce the attention mechanism and build a multi-scale attention model. Discriminative information considers salient objects and regions by means of channel attention and spatial attention. Besides, the central loss function joint supervision strategy is introduced to further reduce the misjudgment of intra-class differences. Second, a model based on multi-level context information is proposed to describe the positional relationship between objects, which can effectively alleviate the influence of the similarity of objects between classes. Finally, the two models are merged to give full play to the compatibility of features, so that the final feature representation not only focuses on the effective discriminant information, but also manifests the relative position relationship between significant objects. Extensive experiments have proved that the method in this paper effectively solves the problem of insufficient feature representation in scene recognition tasks, and improves the accuracy of scene recognition.

A novel method for the estimation of the temperature distribution in a rapid thermal processing (RTP) system is developed in this paper. The proposed method uses a proper orthogonal decomposition algorithm to extract the dominant modes of the temperature distribution and a reduced-order model is obtained. Then, a reduced-order sliding-mode observer is developed to capture the dynamics of the dominant modes. The estimated dynamics of the dominant modes can be used to reconstruct the temperature distribution. It is proved that the estimation error would be drawn into a small boundary rapidly. Test results confirm the effectiveness of the proposed observer for the RTP system.

Motivation: Genome-wide clustered, regularly interspaced, short palindromic repeat (CRISPR)-Cas9 screen has been widely used to interrogate gene functions. However, the rules to design better libraries beg further refinement. Results: We found single guide RNA (sgRNA) outliers are characterized by higher G-nucleotide counts, especially in regions distal from the PAM motif and are associated with stronger off-target activities. Furthermore, using non-targeting sgRNAs as negative controls lead to strong bias, which can be mitigated by using sgRNAs targeting multiple 'safe harbor' regions. Custom-designed screens confirmed our findings and further revealed that 19 nt sgRNAs consistently gave the best signal-to-noise ratio. Collectively, our analysis motivated the design of a new genome-wide CRISPR/Cas9 screen library and uncovered some intriguing properties of the CRISPR-Cas9 system. Availability and implementation: The MAGeCK workflow is available open source at https://bitbucket.org/liulab/mageck_nest under the MIT license. Supplementary information: Supplementary data are available at Bioinformatics online.

In order to control the temperature distribution on the wafer in a rapid thermal processing system, we develop a learning control approach based on the dominant modes of the system state. Firstly, the dominant modes of the system state are extracted through the K-L method. Galerkin's method is utilized to construct the reduced model of the system from the dominant modes. Then learning control approach is designed based on this reduced model. Simulations are performed by heating the wafer from 300K to 1000K with the proposed control method. Simulation results show that the proposed control method has superb ability to reduce the temperature tracking error and improve the temperature uniformity among the wafer.