3D Shape Tokenization via Latent Flow Matching

• URL: http://arxiv.org/abs/2412.15618v3
• Date: Mon, 24 Mar 2025 23:10:37 GMT
• Title: 3D Shape Tokenization via Latent Flow Matching
• Authors: Jen-Hao Rick Chang, Yuyang Wang, Miguel Angel Bautista Martin, Jiatao Gu, Xiaoming Zhao, Josh Susskind, Oncel Tuzel,
• Abstract summary: We introduce a latent 3D representation that models 3D surfaces as probability density functions in 3D, i.e., p(x,y,z), with flow-matching.<n>Our representation is specifically designed for consumption by machine learning models, offering continuity and compactness by construction while requiring only point clouds and minimal data preprocessing.
• Score: 38.28217561449967
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce a latent 3D representation that models 3D surfaces as probability density functions in 3D, i.e., p(x,y,z), with flow-matching. Our representation is specifically designed for consumption by machine learning models, offering continuity and compactness by construction while requiring only point clouds and minimal data preprocessing. Despite being a data-driven method, our use of flow matching in the 3D space enables interesting geometry properties, including the capabilities to perform zero-shot estimation of surface normal and deformation field. We evaluate with several machine learning tasks, including 3D-CLIP, unconditional generative models, single-image conditioned generative model, and intersection-point estimation. Across all experiments, our models achieve competitive performance to existing baselines, while requiring less preprocessing and auxiliary information from training data.

Related papers

• Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration [2.814748676983944]
  We propose a graph neural network model embedded with a local Spherical Euclidean 3D equivariance property through SE(3) message passing based propagation. Our model is composed mainly of a descriptor module, equivariant graph layers, match similarity, and the final regression layers. Experiments conducted on the 3DMatch and KITTI datasets exhibit the compelling and robust performance of our model compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-10-08T06:48:01Z)
• Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation [32.30055363306321]
  We propose a paradigm for seamlessly unifying different human pose and shape-related tasks and datasets. Our formulation is centered on the ability to query any arbitrary point of the human volume, and obtain its estimated location in 3D.
  arXiv  Detail & Related papers  (2024-07-10T10:44:18Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data [50.164670363633704]
  We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets from text prompts. Our model is directly trained on extensive noisy and unaligned in-the-wild' 3D assets. We achieve state-of-the-art performance in both single-class generation and text-to-3D generation.
  arXiv  Detail & Related papers  (2024-06-06T17:58:15Z)
• Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability [118.26563926533517]
  Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. We extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
  arXiv  Detail & Related papers  (2024-02-19T15:33:09Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• Explorable Mesh Deformation Subspaces from Unstructured Generative Models [53.23510438769862]
  Deep generative models of 3D shapes often feature continuous latent spaces that can be used to explore potential variations. We present a method to explore variations among a given set of landmark shapes by constructing a mapping from an easily-navigable 2D exploration space to a subspace of a pre-trained generative model.
  arXiv  Detail & Related papers  (2023-10-11T18:53:57Z)
• Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation [47.945556996219295]
  We present a novel alignment-before-generation approach to generate 3D shapes based on 2D images or texts. Our framework comprises two models: a Shape-Image-Text-Aligned Variational Auto-Encoder (SITA-VAE) and a conditional Aligned Shape Latent Diffusion Model (ASLDM)
  arXiv  Detail & Related papers  (2023-06-29T17:17:57Z)
• 3D VR Sketch Guided 3D Shape Prototyping and Exploration [108.6809158245037]
  We propose a 3D shape generation network that takes a 3D VR sketch as a condition. We assume that sketches are created by novices without art training. Our method creates multiple 3D shapes that align with the original sketch's structure.
  arXiv  Detail & Related papers  (2023-06-19T10:27:24Z)
• 3D Neural Field Generation using Triplane Diffusion [37.46688195622667]
  We present an efficient diffusion-based model for 3D-aware generation of neural fields. Our approach pre-processes training data, such as ShapeNet meshes, by converting them to continuous occupancy fields. We demonstrate state-of-the-art results on 3D generation on several object classes from ShapeNet.
  arXiv  Detail & Related papers  (2022-11-30T01:55:52Z)
• Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images [82.32776379815712]
  We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. We adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network. Our model is robust to the quality of the initial mesh and the error of camera pose, and can be combined with a differentiable function for test-time optimization.
  arXiv  Detail & Related papers  (2022-04-21T03:42:31Z)
• ShapeFormer: Transformer-based Shape Completion via Sparse Representation [41.33457875133559]
  We present ShapeFormer, a network that produces a distribution of object completions conditioned on incomplete, and possibly noisy, point clouds. The resultant distribution can then be sampled to generate likely completions, each exhibiting plausible shape details while being faithful to the input.
  arXiv  Detail & Related papers  (2022-01-25T13:58:30Z)
• Scene Synthesis via Uncertainty-Driven Attribute Synchronization [52.31834816911887]
  This paper introduces a novel neural scene synthesis approach that can capture diverse feature patterns of 3D scenes. Our method combines the strength of both neural network-based and conventional scene synthesis approaches.
  arXiv  Detail & Related papers  (2021-08-30T19:45:07Z)
• Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence [30.849927968528238]
  We propose a novel Deformed Implicit Field representation for modeling 3D shapes of a category. Our neural network, dubbed DIF-Net, jointly learns a shape latent space and these fields for 3D objects belonging to a category. Experiments show that DIF-Net not only produces high-fidelity 3D shapes but also builds high-quality dense correspondences across different shapes.
  arXiv  Detail & Related papers  (2020-11-27T10:45:26Z)
• Towards General Purpose Geometry-Preserving Single-View Depth Estimation [1.9573380763700712]
  Single-view depth estimation (SVDE) plays a crucial role in scene understanding for AR applications, 3D modeling, and robotics. Recent works have shown that a successful solution strongly relies on the diversity and volume of training data. Our work shows that a model trained on this data along with conventional datasets can gain accuracy while predicting correct scene geometry.
  arXiv  Detail & Related papers  (2020-09-25T20:06:13Z)
• Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction [123.62341095156611]
  Implicit functions represented as deep learning approximations are powerful for reconstructing 3D surfaces. Such features are essential in building flexible models for both computer graphics and computer vision. We present methodology that combines detail-rich implicit functions and parametric representations.
  arXiv  Detail & Related papers  (2020-07-22T13:46:14Z)
• PolyGen: An Autoregressive Generative Model of 3D Meshes [22.860421649320287]
  We present an approach which models the mesh directly using a Transformer-based architecture. Our model can condition on a range of inputs, including object classes, voxels, and images. We show that the model is capable of producing high-quality, usable meshes, and establish log-likelihood benchmarks for the mesh-modelling task.
  arXiv  Detail & Related papers  (2020-02-23T17:16:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.