Related papers: BrepGPT: Autoregressive B-rep Generation with Voro…
Currently, considerable strides have been achieved in Point-of-Interest (POI) embedding methodologies, driven by the emergence of novel POI tasks like recommendation and classification. Despite the success of task-specific, end-to-end…
Recent text-to-image generation models have demonstrated incredible success in generating images that faithfully follow input prompts. However, the requirement of using words to describe a desired concept provides limited control over the…
Voronoi diagrams naturally produce convex, watertight, and topologically consistent cells, making them an appealing representation for 3D shape reconstruction. However, standard differentiable Voronoi approaches typically optimize generator…
In this paper, we develop constructive algorithms for generating quasi-uniform point sets and sequences over arbitrary two-dimensional triangular domains. Our proposed method, called the \emph{Voronoi-guided greedy packing} algorithm,…
RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms,…
Image recognition and generation have long been developed independently of each other. With the recent trend towards general-purpose representation learning, the development of general representations for both recognition and generation…
Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost. This work re-thinks this paradigm, introducing a framework…
Segmentation is a fundamental task in computer vision, underpinning pixel-level scene understanding and serving as a cornerstone for applications ranging from autonomous perception to medical image analysis. For complex referring…
Existing auto-regressive mesh generation approaches suffer from ineffective topology preservation, which is crucial for practical applications. This limitation stems from previous mesh tokenization methods treating meshes as simple…
We consider solving high-order semidefinite programming (SDP) relaxations of nonconvex polynomial optimization problems (POPs) that often admit degenerate rank-one optimal solutions. Instead of solving the SDP alone, we propose a new…
We extend our recent curve-evolution framework based on localized B-spline interpolation to present an adaptive Lagrangian framework for the geometric evolution of point-cloud data representing smooth, codimension-one surfaces in…
A Voronoi diagram partitions the plane into convex cells, each containing the points closest to a single generator. Given such a tessellation, the inverse Voronoi problem seeks the generator set \( S \) that produced it. Our algorithm…
Estimating 3D full-body pose from sparse sensor data is a pivotal technique employed for the reconstruction of realistic human motions in Augmented Reality and Virtual Reality. However, translating sparse sensor signals into comprehensive…
Recently, autoregressive models have demonstrated remarkable performance in class-conditional image generation. However, the application of next-token prediction to high-resolution text-to-image generation remains largely unexplored. In…
Deploying foundation models is increasingly constrained by memory footprint, latency, and hardware costs. Post-training compression can mitigate these bottlenecks by reducing the precision of model parameters without significantly degrading…
Monocular head pose estimation is traditionally formulated as direct regression from a single image to an absolute pose. This paradigm forces the network to implicitly internalize a dataset-specific canonical reference frame. In this work,…
We introduce Multi-Object Generative Perception (MultiGP), a generative inverse rendering method for stochastic sampling of all radiometric constituents -- reflectance, texture, and illumination -- underlying object appearance from a single…
Probabilistic language generators are theoretically modeled as discrete stochastic processes, yet standard decoding strategies (Top-k, Top-p) impose static truncation rules that fail to accommodate the dynamic information density of natural…
Accurate triangulation of the domain plays a pivotal role in computing the numerical approximation of the differential operators. A good triangulation is the one which aids in reducing discretization errors. In a standard collocation…
Evaluating the performance of generative models in image synthesis is a challenging task. Although the Fr\'echet Inception Distance is a widely accepted evaluation metric, it integrates different aspects (e.g., fidelity and diversity) of…