Reconstructing complete 3D scenes from extremely sparse viewpoints (e.g., 2-3 wide-baseline images) remains a core yet unsolved challenge. Existing 3D Gaussian Splatting (3DGS) and neural rendering methods degrade severely when view overlap is limited, often producing incomplete or geometrically distorted results. We introduce SplatFusion, a reconstruction framework that requires no training or fine-tuning of diffusion models, instead relying solely on pretrained video diffusion priors to synthesize missing scene content plausibly. Our core idea is a Scene-Consistent Temporal Guidance (SCTG) mechanism that tightly couples 3D structure with generative diffusion models. Specifically, SCTG conditions video diffusion on sequences rendered from the evolving 3DGS representation, enforcing both spatial alignment with geometry and temporal coherence across synthesized frames. These refined views are back-projected to densify and correct the 3D scene iteratively. Extensive experiments on diverse realworld datasets demonstrate that SplatFusion consistently outperforms existing sparse-view reconstruction methods. Evaluations using VLM-based perceptual scores and the MEt3R metric for geometric consistency show clear gains in visual fidelity and temporal coherence, even in scenarios where previous approaches fail. Our training-free framework opens new possibilities for practical 3D reconstruction applications where dense view acquisition is impractical.

The deployment of large language models (LLMs) on extended reality (XR) devices has great potential to advance the field of human-AI interaction. In case of direct, on-device model inference, selecting the appropriate model and device for specific tasks remains challenging. In this paper, we present AIvaluateXR, a comprehensive evaluation framework for benchmarking LLMs running on XR devices. To demonstrate the framework, we deploy 17 selected LLMs across four XR platforms-Magic Leap 2, Meta Quest 3, Vivo X100 s Pro, and Apple Vision Pro-and conduct an extensive evaluation. Our experimental setup measures four key metrics: performance consistency, processing speed, memory usage, and battery consumption. For each of the 68 model-device pairs, we assess performance under varying string lengths, batch sizes, and thread counts, analyzing the tradeoffs for real-time XR applications. We finally propose a unified evaluation method based on the 3D Pareto Optimality theory to select the optimal device-model pairs from the quality and speed objectives. Additionally, we compare the efficiency of on-device LLMs with client-server and cloud-based setups, and evaluate their accuracy on two interactive tasks. We believe our findings offer valuable insights to guide future optimization efforts for LLM deployment on XR devices. Our evaluation method can be followed as standard groundwork for further research and development in this emerging field.

We introduce DiffFit, a differentiable algorithm for fitting protein atomistic structures into an experimental reconstructed Cryo-Electron Microscopy (cryo-EM) volume map. In structural biology, this process is necessary to semi-automatically composite large mesoscale models of complex protein assemblies and complete cellular structures that are based on measured cryo-EM data. The current approaches require manual fitting in three dimensions to start, resulting in approximately aligned structures followed by an automated fine-tuning of the alignment. The DiffFit approach enables domain scientists to fit new structures automatically and visualize the results for inspection and interactive revision. The fitting begins with differentiable three-dimensional (3D) rigid transformations of the protein atom coordinates followed by sampling the density values at the atom coordinates from the target cryo-EM volume. To ensure a meaningful correlation between the sampled densities and the protein structure, we proposed a novel loss function based on a multi-resolution volume-array approach and the exploitation of the negative space. This loss function serves as a critical metric for assessing the fitting quality, ensuring the fitting accuracy and an improved visualization of the results. We assessed the placement quality of DiffFit with several large, realistic datasets and found it to be superior to that of previous methods. We further evaluated our method in two use cases: automating the integration of known composite structures into larger protein complexes and facilitating the fitting of predicted protein domains into volume densities to aid researchers in identifying unknown proteins. We implemented our algorithm as an open-source plugin (github.com/nanovis/DiffFit) in ChimeraX, a leading visualization software in the field. All supplemental materials are available at osf. io/5tx4q.

The authors would like to make the following errata after correcting the initialization related bugs in the associated program.

Dr. KID is an algorithm that uses isometric decomposition for the physicalization of potato-shaped organic models in a puzzle fashion. The algorithm begins with creating a simple, regular triangular surface mesh of organic shapes, followed by iterative K-means clustering and remeshing. For clustering, we need similarity between triangles (segments) which is defined as a distance function. The distance function maps each triangle's shape to a single point in the virtual 3D space. Thus, the distance between the triangles indicates their degree of dissimilarity. K-means clustering uses this distance and sorts segments into k classes. After this, remeshing is applied to minimize the distance between triangles within the same cluster by making their shapes identical. Clustering and remeshing are repeated until the distance between triangles in the same cluster reaches an acceptable threshold. We adopt a curvature-aware strategy to determine the surface thickness and finalize puzzle pieces for 3D printing. Identical hinges and holes are created for assembling the puzzle components. For smoother outcomes, we use triangle subdivision along with curvature-aware clustering, generating curved triangular patches for 3D printing. Our algorithm was evaluated using various models, and the 3D-printed results were analyzed. Findings indicate that our algorithm performs reliably on target organic shapes with minimal loss of input geometry.

Abstract Augmented Virtual Environments (AVE) or Virtual‐Reality Fusion systems fuse dynamic videos with static three‐dimensional (3D) models of a virtual environment to provide an optimal solution for visualizing and understanding multichannel surveillance systems. However, texture distortion caused by viewpoint changes in such systems is a critical issue that needs to be addressed. To minimize texture fusion distortion, this paper presents a novel virtual environment system in two phases, offline and online phases, to dynamically fuse multiple surveillance videos with a virtual 3D scene. In the offline phase, a static virtual environment is obtained by performing a 3D photogrammetric reconstruction from the input images of the scene. In the online phase, the virtual environment is augmented by fusing multiple videos through two optional strategies. One strategy is to dynamically map images of different videos onto a 3D model of the virtual environment, and the other is to extract moving objects and represent them as billboards. The system can be used to visualize a 3D environment from any viewpoint augmented by real‐time videos. Experiments and user studies in different scenarios demonstrate the superiority of our system.

Triangle meshes are used in many important shape-related applications including geometric modeling, animation production, system simulation, and visualization. However, these meshes are typically generated in raw form with several defects and poor-quality elements, obstructing them from practical application. Over the past decades, different surface remeshing techniques have been presented to improve these poor-quality meshes prior to the downstream utilization. A typical surface remeshing algorithm converts an input mesh into a higher quality mesh with consideration of given quality requirements as well as an acceptable approximation to the input mesh. In recent years, surface remeshing has gained significant attention from researchers and engineers, and several remeshing algorithms have been proposed. However, there has been no survey article on remeshing methods in general with a defined search strategy and article selection mechanism covering the recent approaches in surface remeshing domain with a good connection to classical approaches. In this article, we present a survey on surface remeshing techniques, classifying all collected articles in different categories and analyzing specific methods with their advantages, disadvantages, and possible future improvements. Following the systematic literature review methodology, we define step-by-step guidelines throughout the review process, including search strategy, literature inclusion/exclusion criteria, article quality assessment, and data extraction. With the aim of literature collection and classification based on data extraction, we summarized collected articles, considering the key remeshing objectives, the way the mesh quality is defined and improved, and the way their techniques are compared with other previous methods. Remeshing objectives are described by angle range control, feature preservation, error control, valence optimization, and remeshing compatibility. The metrics used in the literature for the evaluation of surface remeshing algorithms are discussed. Meshing techniques are compared with other related methods via a comprehensive table with indices of the method name, the remeshing challenge met and solved, the category the method belongs to, and the year of publication. We expect this survey to be a practical reference for surface remeshing in terms of literature classification, method analysis, and future prospects.

Surface remeshing is widely required in modeling, animation, simulation, and many other computer graphics applications. Improving the elements’ quality is a challenging task in surface remeshing. Existing methods often fail to efficiently remove poor-quality elements especially in regions with sharp features. In this paper, we propose and use a robust segmentation method followed by remeshing the segmented mesh. Mesh segmentation is initiated using an existing Live-wire interaction approach and is further refined using local mesh operations. The refined segmented mesh is finally sent to the remeshing pipeline, in which each mesh segment is remeshed independently. An experimental study compares our mesh segmentation method as well as remeshing results with representative existing methods. We demonstrate that the proposed segmentation method is robust and suitable for remeshing.

The performance of Deep Reinforcement Learning (DRL) algorithms is usually constrained by instability and variability. In this work, we present an extension of Deep Q-Network (DQN) called Deep Deformable Q-Network which is based on deformable convolution mechanisms. The new algorithm can readily be built on existing models and can be easily trained end-to-end by standard back-propagation. Extensive experiments on the Atari games validate the feasibility and effectiveness of the proposed Deep Deformable Q-Network.