ShapeAssembly

arXiv (Cornell University), 2023

arXiv (Cornell University), 2023

We present a significant breakthrough in 3D shape generation by scaling it to unprecedented dimensions. Through the adaptation of the Auto-Regressive model and the utilization of large language models, we have developed a remarkable model with an astounding 3.6 billion trainable parameters, establishing it as the largest 3D shape generation model to date, named Argus-3D. Our approach addresses the limitations of existing methods by enhancing the quality and diversity of generated 3D shapes. To tackle the challenges of high-resolution 3D shape generation, our model incorporates tri-plane features as latent representations, effectively reducing computational complexity. Additionally, we introduce a discrete codebook for efficient quantization of these representations. Leveraging the power of transformers, we enable multi-modal conditional generation, facilitating the production of diverse and visually impressive 3D shapes. To train our expansive model, we leverage an ensemble of publicly-available 3D datasets, consisting of a comprehensive collection of approximately 900,000 objects from renowned repositories such as ModelNet40, ShapeNet, Pix3D, 3D-Future, and Objaverse. This diverse dataset empowers our model to learn from a wide range of object variations, bolstering its ability to generate high-quality and diverse 3D shapes. Through extensive experimentation, we demonstrate the remarkable efficacy of our approach in significantly improving the visual quality of generated 3D shapes. By pushing the boundaries of 3D generation, introducing novel methods for latent representation learning, and harnessing the power of transformers for multi-modal conditional generation, our contributions pave the way for substantial advancements in the field. Our work unlocks new possibilities for applications in gaming, virtual reality, product design, and other domains that demand high-quality and diverse 3D objects. Project page and code: .

IEEE Transactions on Visualization and Computer Graphics, 2021

We introduce a modeling tool which can evolve a set of 3D objects in a functionality-aware manner. Our goal is for the evolution to generate large and diverse sets of plausible 3D objects for data augmentation, constrained modeling, as well as open-ended exploration to possibly inspire new designs. Starting with an initial population of 3D objects belonging to one or more functional categories, we evolve the shapes through part recombination to produce generations of hybrids or crossbreeds between parents from the heterogeneous shape collection. Evolutionary selection of offsprings is guided both by a functional plausibility score derived from functionality analysis of shapes in the initial population and user preference, as in a design gallery. Since cross-category hybridization may result in offsprings not belonging to any of the known functional categories, we develop a means for functionality partial matching to evaluate functional plausibility on partial shapes. We show a variety of plausible hybrid shapes generated by our functionality-aware model evolution, which can complement existing datasets as training data and boost the performance of contemporary data-driven segmentation schemes, especially in challenging cases. Our tool supports constrained modeling, allowing users to restrict or steer the model evolution with functionality labels. At the same time, unexpected yet functional object prototypes can emerge during open-ended exploration owing to structure breaking when evolving a heterogeneous collection.

Random Sampling Silhouettes Reconstructions Figure 1: Left: Our method generates multi-view depth maps and silhouettes, and uses a rendering function to obtain the 3D shapes. Right: We can also extend our framework to reconstruct 3D shapes from single/multi-view depth maps or silhouettes. Abstract We study the problem of learning generative models of 3D shapes. Voxels or 3D parts have been widely used as the underlying representations to build complex 3D shapes; however, voxel-based representations suffer from high memory requirements, and parts-based models require a large collection of cached or richly parametrized parts. We take an alternative approach: learning a generative model over multi-view depth maps or their corresponding silhouettes, and using a deterministic rendering function to produce 3D shapes from these images. A multi-view representation of shapes enables generation of 3D models with fine details , as 2D depth maps and silhouettes can be modeled at a much higher resolution than 3D voxels. Moreover, our approach naturally brings the ability to recover the underlying 3D representation from depth maps of one or a few viewpoints. Experiments show that our framework can generate 3D shapes with variations and details. We also demonstrate that our model has out-of-sample generalization power for real-world tasks with occluded objects. Code and data here: https://github.com/Amir-Arsalan/Synthesize3DviaDepthOrSil

2020

Sequential assembly with geometric primitives has drawn attention in robotics and 3D vision since it yields a practical blueprint to construct a target shape. However, due to its combinatorial property, a greedy method falls short of generating a sequence of volumetric primitives. To alleviate this consequence induced by a huge number of feasible combinations, we propose a combinatorial 3D shape generation framework. The proposed framework reflects an important aspect of human generation processes in real life – we often create a 3D shape by sequentially assembling unit primitives with geometric constraints. To find the desired combination regarding combination evaluations, we adopt Bayesian optimization, which is able to exploit and explore efficiently the feasible regions constrained by the current primitive placements. An evaluation function conveys global structure guidance for an assembly process and stability in terms of gravity and external forces simultaneously. Experimental...

arXiv (Cornell University), 2019

A long-standing problem in shape analysis and synthesis is how to build generative models that support the creation of new, diverse, and realistic shapes. A key challenge is to accommodate diverse shape variations, including both continuous deformations of parts as well as structural or discrete alterations which add, remove, or modify the shape substructures present. We seek a continuous latent space that can incorporate all this diversity [Hinton 1990] and is able to encode, for example, chairs with or without armrests, chairs having four legs or swivel bases, as well as high or low backs, thin or thick legs, etc. Such a latent space, in turn, enables many non-trivial applications including generating shapes with both novel structure and geometry, discovering object structures from raw unannotated

Proceedings of the tenth international conference on 3D Web technology - Web3D '05, 2005

This paper proposes a novel, yet extremely compact model representation method. Its main feature is that 3D shapes are represented in terms of functions instead of geometric primitives. Given a set of -typically only a few -specific parameters, the evaluation of such a function results in a model that is one instance of a general shape. Particularly important for the web context with client systems of widely varying rendering performance is the support of a semantic level-of-detail superior to any low-level polygon reduction scheme.

arXiv (Cornell University), 2023

Implicit generative models have been widely employed to model 3D data and have recently proven to be successful in encoding and generating high-quality 3D shapes. This work builds upon these models and alleviates current limitations by presenting the first implicit generative model that facilitates the generation of complex 3D shapes with rich internal geometric details. To achieve this, our model uses unsigned distance fields to represent nested 3D surfaces allowing learning from non-watertight mesh data. We propose a transformer-based autoregressive model for 3D shape generation that leverages context-rich tokens from vector quantized shape embeddings. The generated tokens are decoded into an unsigned distance field which is rendered into a novel 3D shape exhibiting a rich internal structure. We demonstrate that our model achieves state-of-theart point cloud generation results on popular classes of 'Cars', 'Planes', and 'Chairs' of the ShapeNet dataset. Additionally, we curate a dataset that exclusively comprises shapes with realistic internal details from the 'Cars' class of ShapeNet and demonstrate our method's efficacy in generating these shapes with internal geometry.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

We explore the interpretability of 3D geometric deep learning models in the context of Computer-Aided Design (CAD). The field of parametric CAD can be limited by the difficulty of expressing high-level design concepts in terms of a few numeric parameters. In this paper, we use a deep learning architectures to encode high dimensional 3D shapes into a vectorized latent representation that can be used to describe arbitrary concepts. Specifically, we train a simple auto-encoder to parameterize a dataset of complex shapes. To understand the latent encoded space, we use the idea of Concept Activation Vectors (CAV) to reinterpret the latent space in terms of user-defined concepts. This allows modification of a reference design to exhibit more or fewer characteristics of a chosen concept or group of concepts. We also test the statistical significance of the identified concepts and determine the sensitivity of a physical quantity of interest across the dataset.

Computer Graphics Forum, 2021

We introduce an approach to incorporate user guidance into shape generation approaches based on deep networks. Generative networks such as autoencoders and generative adversarial networks are trained to encode shapes into latent vectors, effectively learning a latent shape space that can be sampled for generating new shapes. Our main idea is to enable users to explore the shape space with the use of high‐level semantic keywords. Specifically, the user inputs a set of keywords that describe the general attributes of the shape to be generated, e.g., “four legs” for a chair. Then, our method maps the keywords to a subspace of the latent space, where the subspace captures the shapes possessing the specified attributes. The user then explores only this subspace to search for shapes that satisfy the design goal, in a process similar to using a parametric shape model. Our exploratory approach allows users to model shapes at a high level without the need for advanced artistic skills, in con...