论文检索
输入标题、作者或关键词，从 326 篇学术成果中精准定位
Reconstructing high-fidelity, animatable, and relightable 3D hand avatars from a single RGB image is a challenging yet critical task for immersive VR/AR applications. State-of-the-art hand reconstruction methods achieve impressive reconstruction and relighting results, but they mostly leverage dense observations, such as multi-view images or monocular video sequences and rely on per-scene optimization. Moreover, it is difficult for these methods to generate plausible appearance in occluded regions. In contrast, existing single-view hand reconstruction methods typically struggle to disentangle global illumination, resulting in textures with baked-in shading artifacts. To address these challenges, we propose FLASHand, the first feed-forward relightable and animatable 3D hand reconstruction model from a single RGB image. Our method bridges the gap between efficiency and fidelity, enabling instant creation of personalized hand avatars with disentangled appearance that can be rendered under novel lighting and poses. To ensure plausible geometry generation and achieve high-fidelity animation and relighting, we introduce a mesh-based disentangled 2D Gaussian splatting hand representation. We leverage the NIMBLE parametric prior to define a canonical attribute space, and define geometry and appearance attributes explicitly. We then propose the Feed-forward Hand Attributes Generator (FHAG) to predict these attributes from a single image. By leveraging a cross attention module to fuse canonical geometric information with input image features, FHAG effectively lifts pixel-level visual cues into the 3D hand canonical space, directly generating spatially-aligned geometry and appearance attributes. This allows us to bypass iterative optimization and instantly reconstruct a high-fidelity hand avatar from a single RGB image. Extensive experiments on both synthetic and in-the-wild datasets demonstrate that FLASHand achieves state-of-the-art performance in novel view synthesis and supports real-time animation and relighting. Code and data are available at https://github.com/IGLICT/FLASHand.
Monocular video–based human mesh recovery (HMR) has made significant progress in recent years, yet existing methods often fail to reconstruct physically plausible motion during highly dynamic airborne movements such as jumping or acrobatics. These failure cases arise from motion blur, rapid orientation changes, and the lack of suitable training data, leading to temporally inconsistent and physically implausible results. We propose a novel method for reconstructing 3D airborne motion by refining inaccurate estimates produced by state-of-the-art HMR systems. Our approach extracts key physical quantities, identifies reliable motion segments based on physical consistency, and connects them using a homotopy-aware trajectory optimization. A global angular momentum constraint is then enforced over the entire motion, and global motion and local poses are jointly optimized under physical and temporal smoothness constraints. Experiments on challenging in-the-wild videos demonstrate that our method produces more physically consistent and temporally coherent airborne motions than existing refinement approaches.
Rigid-deployable Kirigami sheets are unique mechanical structures, enabling extreme expansion with minimal elastic deformation. Furthermore, they unfold in fluid and coordinated motions which reveal interesting geometric patterns. Thanks to their tunable expansion behaviour, Kirigami-like structures have found a wide range of applications at various scales. However, finding the right geometry for a given application remains a significant challenge due to the complex relationship between cut patterns and deployment behavior. In this work, we introduce a computational approach to explore the design space of rigid-deployable Kirigami sheets defined over isohedral tilings, a class of periodic patterns constructed from identical polygonal tiles. Our method explores the mixed discrete-continuous design space formed by joint topologies and tile shape parameters. Leveraging tools from linkage analysis, we identify self-deployable designs with a single kinematic degree of freedom. To compute the corresponding deployment motions, we extend the concept of nonlinear compliant modes to the multi-body setting, incorporating collision handling to ensure feasible designs. Our approach enables the discovery of diverse isohedral Kirigami sheets with varying topologies, tile shapes, and expansion behavior. We showcase our results through an interactive material browser and validate selected designs with 3D-printed prototypes. Code and data for this paper are available at https://github.com/guo-han/Isogami.
Manufacturability is crucial for reliable product design, with cutter accessibility being a fundamental constraint in subtractive manufacturing. Traditional geometric methods are accurate but computationally expensive, while learning-based approaches often lack conservativeness and generalization, leading to unsafe predictions. In this paper, we introduce DeepMill++, a conservative and highly efficient framework for cutter accessibility analysis on arbitrary triangular meshes. Instead of relying on neural networks as end-to-end predictors, DeepMill++ reformulates accessibility and occlusion detection as a rasterization-based visibility and depth pooling problem, enabling fast and controllable geometric verification on the GPU. A neural network is used only to guide the evaluation order of cutter directions and vertices, significantly reducing redundant computations while preserving strict conservativeness. Experiments show that DeepMill++ achieves up to 9.5× speedup over state-of-the-art geometric methods under matched accuracy, while maintaining 97.5% conservative accessibility accuracy. For meshes up to 125K triangles, full analysis completes in 2.9 seconds, enabling interactive design and large-scale path planning. The method supports general mesh types and diverse cutter sizes without category assumptions.
We present a compact yet highly expressive design space for shellular metamaterials that support both interactive exploration and inverse design. With only a few dozen charges, our representation generates a wide family of periodic shells, spanning from simple planar configurations to complex TPMS-like morphologies. To enable rapid evaluation, we introduce an efficient GPU-based homogenization pipeline that computes the effective elastic tensor of a candidate design in near real time (∼ 0.4 s), making interactive shellular design practical. Across a large set of synthesized structures, our design space exhibits geometric diversity and spans a broad spectrum of mechanical responses, covering a wide range of effective material properties. This fast evaluation further enables inverse design for target macroscopic properties. In the low-solid-volume regime, the resulting shellular structures achieve performance competitive with state-of-the-art shell-based metamaterials in multiple material properties. Finally, we validate manufacturability by fabricating tiled prototypes via additive manufacturing, demonstrating the potential of our approach for real-world engineering applications.
该来源暂未提供摘要。
Signed Distance Fields (SDFs) are a powerful volumetric representation for 3D geometry. Recent advances in surface generation from SDFs increasingly rely on learnable surface representations and direct mesh supervision. In this work, we challenge this trend and show that high-quality surface reconstruction can be achieved by learning to refine the volumetric signal itself. We present SuperSDF, a learning-based approach for sparse SDF super-resolution that operates directly in SDF space, without auxiliary surface representations or mesh-level supervision. Using a sparse voxel neural network restricted to a narrow band near the surface, our method predicts high-resolution signed-distance values from coarse inputs in a scalable and resolution-agnostic manner. Standard isosurface extraction algorithms can then process the resulting super-resolved SDFs to produce accurate, detailed surface meshes. Our results show that learning-based SDF upsampling alone is sufficient to recover fine geometric details missed by classical interpolation and prior reconstruction methods. Compared to state-of-the-art machine learning approaches, our method generates higher-fidelity surfaces at a fraction of the computational cost and scales to volumetric resolutions that were previously impractical.
Voronoi diagrams, and their more general weighted counterpart, power diagrams, are fundamental geometric constructs with wide-ranging applications in biology, physics simulation, and computer graphics. Recently, they have gained renewed attention in mesh-based neural rendering. Despite being extensively studied, the construction of 3D Voronoi diagrams for large-scale point sets remains computationally expensive, limiting their adoption in large-scale applications. Existing CPU-based approaches typically rely on computing its dual, the Delaunay tetrahedralization, but are prohibitively slow for large diagrams, while GPU-based methods either struggle to scale efficiently to large point sets or assume homogeneous point distributions. The weighted case, power diagrams, is even less explored in this context. Existing approaches are typically tailored to the application at hand, assuming homogeneous point distributions and small weight variations, making them unsuitable for general use in more complex heterogeneous data. In this paper, we present a highly parallelizable GPU algorithm for the fast construction of large-scale 3D Voronoi and power diagrams. Our approach constructs each convex cell from a weighted 3D point by progressively clipping an initial cell volume against bisecting planes induced by candidate neighboring points. To efficiently identify candidate neighbors under arbitrary spatial distributions, we introduce a culling criterion based on directional geometric bounds of the evolving cell, combined with a hierarchical best-first traversal of bounding volumes. We achieve performance on par with state-of-the-art Delaunay tetrahedralization methods on small and moderate problem sizes, while exhibiting robust scalability to large point sets and diverse spatial distributions. Moreover, our method naturally generalizes to power diagrams without additional assumptions. To facilitate reproducibility and future research, we release our source code, see https://research.zenseact.com/publications/paragram.
2D constrained Delaunay triangulation (CDT) is a key component in CAD, visualization, and scientific computing. We present a highly parallel GPU-based method capable of computing CDTs on inputs with millions of vertices, while efficiently and robustly enforcing arbitrary valid constraints. On benchmarks with complex constraints, our method typically delivers several-fold speedups over the prior state-of-the-art GPU approach and is roughly an order of magnitude faster than widely used CPU implementations. The efficiency stems from an improved parallel edge-flipping scheme and a constraint-handling algorithm with predictable parallel behavior, enabling stable performance even on adversarial and difficult configurations.
Achieving high-quality real-time rendering on mobile devices is critical for immersive 3D applications, yet 3D Gaussian Splatting (3DGS) faces significant challenges on resource-constrained mobile platforms, with sustaining 60 FPS at 2K resolution remaining difficult despite recent advances. Rather than further optimizing the core splatting pipeline, we explore 3DGS acceleration through post-rendering techniques leveraging gradient for super-sampling and frame interpolation. We propose Mobile3DGS3, a lightweight framework that alternates between super-sampling and frame interpolation. Our framework introduces three key innovations: Tangent Space Gradient Caching (TSGC), which converts gradient into cached geometric invariants enabling seamless integration with hardware-accelerated rasterization; Gradient-Aware Super-Sampling (GASS), which leverages Gaussian splat differentiability to upsample low-resolution images while preserving details; and Gradient-Aware Frame Interpolation (GAFI), which resamples gradient from adjacent frames with efficient motion vector upscaling for NPU-compatible processing. Extensive experiments demonstrate significant rendering efficiency improvements on mobile devices while maintaining high visual fidelity, presenting the first 3DGS acceleration paradigm on mobile devices that effectively leverages gradient in both super-sampling and frame interpolation. Code repository: https://github.com/SyouSanGin/Mobile3DGS3