Related papers: Scaling Mesh Generation via Compressive Tokenizati…

We consider the task of generating realistic 3D shapes, which is useful for a variety of applications such as automatic scene generation and physical simulation. Compared to other 3D representations like voxels and point clouds, meshes are…

Large Language Models have proven highly successful at modelling a variety of tasks. However, this comes at a steep computational cost that hinders wider industrial uptake. In this paper, we present MWT: a Multi-Word Tokenizer that goes…

Masked generative models (MGMs) can generate tokens in parallel and in any order, unlike autoregressive models (ARMs), which decode one token at a time, left-to-right. However, MGMs process the full-length sequence at every sampling step,…

Mesh generation plays a crucial role in scientific computing. Traditional mesh generation methods, such as TFI and PDE-based methods, often struggle to achieve a balance between efficiency and mesh quality. To address this challenge,…

Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based representations discard deterministic spatial ordering,…

As large language models move toward million-token context windows, CPU tokenizers become a major slowdown because they process text one step at a time while powerful GPUs sit unused. We built a GPU-based byte-level BPE tokenizer that…

Skeleton generation is essential for animating 3D assets, but current deep learning methods remain limited: they cannot handle the growing structural complexity of modern models and offer minimal controllability, creating a major bottleneck…

Traditional methods of reconstructing 3D human pose and mesh from single images rely on paired image-mesh datasets, which can be difficult and expensive to obtain. Due to this limitation, model scalability is constrained as well as…

Polygonal meshes are ubiquitous in the digital 3D domain, yet they have only played a minor role in the deep learning revolution. Leading methods for learning generative models of shapes rely on implicit functions, and generate meshes only…

We introduce Scan2Mesh, a novel data-driven generative approach which transforms an unstructured and potentially incomplete range scan into a structured 3D mesh representation. The main contribution of this work is a generative neural…

Mesh generation remains a key technology in many areas where numerical simulations are required. As numerical algorithms become more efficient and computers become more powerful, the percentage of time devoted to mesh generation becomes…

The Byte Pair Encoding algorithm can be safely batched to merge hundreds of pairs of tokens at a time when building up a tokenizer's vocabulary. This technique combined with reducing the memory footprint of text used in vocabulary training…

Medical image segmentation is essential for clinical diagnosis and treatment planning. Although transformer-based methods have achieved remarkable results, their high computational cost hinders clinical deployment. To address this issue, we…

Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks…

We are interested in reconstructing the mesh representation of object surfaces from point clouds. Surface reconstruction is a prerequisite for downstream applications such as rendering, collision avoidance for planning, animation, etc.…

Mesh is a fundamental representation of 3D assets in various industrial applications, and is widely supported by professional softwares. However, due to its irregular structure, mesh creation and manipulation is often time-consuming and…

We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in existing methods, including the limited dataset scale when…

Polygonal meshes have become the standard for discretely approximating 3D shapes, thanks to their efficiency and high flexibility in capturing non-uniform shapes. This non-uniformity, however, leads to irregularity in the mesh structure,…

This paper presents a compact model architecture called MOGNET, compatible with a resource-limited hardware. MOGNET uses a streamlined Convolutional factorization block based on a combination of 2 point-wise (1x1) convolutions with a…

The generation of quadrilateral-dominant meshes is a cornerstone of professional 3D content creation. However, existing generative models generate quad meshes by first generating triangle meshes and then merging triangles into…