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 results demonstrate that our method successfully generates combinatorial 3D shapes and simulates more realistic generation processes. We also introduce a new dataset for combinatorial 3D shape generation. All the codes are available at \url{https://github.com/POSTECH-CVLab/Combinatorial-3D-Shape-Generation}.
3D generative shape modeling is a fundamental research area in computer vision and interactive computer graphics, with many real-world applications. This paper investigates the novel problem of generating 3D shape point cloud geometry from a symbolic part tree representation. In order to learn such a conditional shape generation procedure in an end-to-end fashion, we propose a conditional GAN "part tree"-to-"point cloud" model (PT2PC) that disentangles the structural and geometric factors. The proposed model incorporates the part tree condition into the architecture design by passing messages top-down and bottom-up along the part tree hierarchy. Experimental results and user study demonstrate the strengths of our method in generating perceptually plausible and diverse 3D point clouds, given the part tree condition. We also propose a novel structural measure for evaluating if the generated shape point clouds satisfy the part tree conditions.
Polygon meshes are an efficient representation of 3D geometry, and are of central importance in computer graphics, robotics and games development. Existing learning-based approaches have avoided the challenges of working with 3D meshes, instead using alternative object representations that are more compatible with neural architectures and training approaches. We present an approach which models the mesh directly, predicting mesh vertices and faces sequentially using a Transformer-based architecture. Our model can condition on a range of inputs, including object classes, voxels, and images, and because the model is probabilistic it can produce samples that capture uncertainty in ambiguous scenarios. We show that the model is capable of producing high-quality, usable meshes, and establish log-likelihood benchmarks for the mesh-modelling task. We also evaluate the conditional models on surface reconstruction metrics against alternative methods, and demonstrate competitive performance despite not training directly on this task.
Recent advances in 3D deep learning have shown that it is possible to train highly effective deep models for 3D shape generation, directly from 2D images. This is particularly interesting since the availability of 3D models is still limited compared to the massive amount of accessible 2D images, which is invaluable for training. The representation of 3D surfaces itself is a key factor for the quality and resolution of the 3D output. While explicit representations, such as point clouds and voxels, can span a wide range of shape variations, their resolutions are often limited. Mesh-based representations are more efficient but are limited by their ability to handle varying topologies. Implicit surfaces, however, can robustly handle complex shapes, topologies, and also provide flexible resolution control. We address the fundamental problem of learning implicit surfaces for shape inference without the need of 3D supervision. Despite their advantages, it remains nontrivial to (1) formulate a differentiable connection between implicit surfaces and their 2D renderings, which is needed for image-based supervision; and (2) ensure precise geometric properties and control, such as local smoothness. In particular, sampling implicit surfaces densely is also known to be a computationally demanding and very slow operation. To this end, we propose a novel ray-based field probing technique for efficient image-to-field supervision, as well as a general geometric regularizer for implicit surfaces, which provides natural shape priors in unconstrained regions. We demonstrate the effectiveness of our framework on the task of single-view image-based 3D shape digitization and show how we outperform state-of-the-art techniques both quantitatively and qualitatively.
We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image. During training, our network gets the learning signal from a silhouette of an object in the input image - a form of self-supervision. It does not require ground truth data for 3D shapes and the viewpoints. Because it relies on such a weak form of supervision, our approach can easily be applied to real-world data. We demonstrate that our method produces reasonable qualitative and quantitative results on natural images for both shape estimation and viewpoint prediction. Unlike previous approaches, our method does not require multiple views of the same object instance in the dataset, which significantly expands the applicability in practical robotics scenarios. We showcase it by using the hallucinated shapes to improve the performance on the task of grasping real-world objects both in simulation and with a PR2 robot.
Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent representations of generative models. However, it remains an open problem to learn a generative model of shape that is interpretable and easily manipulated, particularly in the absence of supervised labels. In this paper, we propose an unsupervised approach to partitioning the latent space of a variational autoencoder for 3D point clouds in a natural way, using only geometric information. Our method makes use of tools from spectral differential geometry to separate intrinsic and extrinsic shape information, and then considers several hierarchical disentanglement penalties for dividing the latent space in this manner, including a novel one that penalizes the Jacobian of the latent representation of the decoded output with respect to the latent encoding. We show that the resulting representation exhibits intuitive and interpretable behavior, enabling tasks such as pose transfer and pose-aware shape retrieval that cannot easily be performed by models with an entangled representation.
We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape. We demonstrate that the learned elementary 3D structures lead to clear improvements in 3D shape generation and matching. More precisely, we present two complementary approaches for learning elementary structures: (i) patch deformation learning and (ii) point translation learning. Both approaches can be extended to abstract structures of higher dimensions for improved results. We evaluate our method on two tasks: reconstructing ShapeNet objects and estimating dense correspondences between human scans (FAUST inter challenge). We show 16% improvement over surface deformation approaches for shape reconstruction and outperform FAUST inter challenge state of the art by 6%.
The ability to generate novel, diverse, and realistic 3D shapes along with associated part semantics and structure is central to many applications requiring high-quality 3D assets or large volumes of realistic training data. A key challenge towards this goal is how to accommodate diverse shape variations, including both continuous deformations of parts as well as structural or discrete alterations which add to, remove from, or modify the shape constituents and compositional structure. Such object structure can typically be organized into a hierarchy of constituent object parts and relationships, represented as a hierarchy of n-ary graphs. We introduce StructureNet, a hierarchical graph network which (i) can directly encode shapes represented as such n-ary graphs; (ii) can be robustly trained on large and complex shape families; and (iii) can be used to generate a great diversity of realistic structured shape geometries. Technically, we accomplish this by drawing inspiration from recent advances in graph neural networks to propose an order-invariant encoding of n-ary graphs, considering jointly both part geometry and inter-part relations during network training. We extensively evaluate the quality of the learned latent spaces for various shape families and show significant advantages over baseline and competing methods. The learned latent spaces enable several structure-aware geometry processing applications, including shape generation and interpolation, shape editing, or shape structure discovery directly from un-annotated images, point clouds, or partial scans.
Three-dimensional human body models are widely used in the analysis of human pose and motion. Existing models, however, are learned from minimally-clothed 3D scans and thus do not generalize to the complexity of dressed people in common images and videos. Additionally, current models lack the expressive power needed to represent the complex non-linear geometry of pose-dependent clothing shapes. To address this, we learn a generative 3D mesh model of clothed people from 3D scans with varying pose and clothing. Specifically, we train a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making clothing an additional term in SMPL. Our model is conditioned on both pose and clothing type, giving the ability to draw samples of clothing to dress different body shapes in a variety of styles and poses. To preserve wrinkle detail, our Mesh-VAE-GAN extends patchwise discriminators to 3D meshes. Our model, named CAPE, represents global shape and fine local structure, effectively extending the SMPL body model to clothing. To our knowledge, this is the first generative model that directly dresses 3D human body meshes and generalizes to different poses. The model, code and data are available for research purposes at https://cape.is.tue.mpg.de.
3D shape generation is a challenging problem due to the high-dimensional output space and complex part configurations of real-world objects. As a result, existing algorithms experience difficulties in accurate generative modeling of 3D shapes. Here, we propose a novel factorized generative model for 3D shape generation that sequentially transitions from coarse to fine scale shape generation. To this end, we introduce an unsupervised primitive discovery algorithm based on a higher-order conditional random field model. Using the primitive parts for shapes as attributes, a parameterized 3D representation is modeled in the first stage. This representation is further refined in the next stage by adding fine scale details to shape. Our results demonstrate improved representation ability of the generative model and better quality samples of newly generated 3D shapes. Further, our primitive generation approach can accurately parse common objects into a simplified representation.
In this paper, we investigate a novel problem of using generative adversarial networks in the task of 3D shape generation according to semantic attributes. Recent works map 3D shapes into 2D parameter domain, which enables training Generative Adversarial Networks (GANs) for 3D shape generation task. We extend these architectures to the conditional setting, where we generate 3D shapes with respect to subjective attributes defined by the user. Given pairwise comparisons of 3D shapes, our model performs two tasks: it learns a generative model with a controlled latent space, and a ranking function for the 3D shapes based on their multi-chart representation in 2D. The capability of the model is demonstrated with experiments on HumanShape, Basel Face Model and reconstructed 3D CUB datasets. We also present various applications that benefit from our model, such as multi-attribute exploration, mesh editing, and mesh attribute transfer.
Applications in virtual and augmented reality create a demand for rapid creation and easy access to large sets of 3D models. An effective way to address this demand is to edit or deform existing 3D models based on a reference, e.g., a 2D image which is very easy to acquire. Given such a source 3D model and a target which can be a 2D image, 3D model, or a point cloud acquired as a depth scan, we introduce 3DN, an end-to-end network that deforms the source model to resemble the target. Our method infers per-vertex offset displacements while keeping the mesh connectivity of the source model fixed. We present a training strategy which uses a novel differentiable operation, mesh sampling operator, to generalize our method across source and target models with varying mesh densities. Mesh sampling operator can be seamlessly integrated into the network to handle meshes with different topologies. Qualitative and quantitative results show that our method generates higher quality results compared to the state-of-the art learning-based methods for 3D shape generation. Code is available at github.com/laughtervv/3DN.
In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data. 3D capsule networks arise as a direct consequence of our novel unified 3D auto-encoder formulation. Their dynamic routing scheme and the peculiar 2D latent space deployed by our approach bring in improvements for several common point cloud-related tasks, such as object classification, object reconstruction and part segmentation as substantiated by our extensive evaluations. Moreover, it enables new applications such as part interpolation and replacement.
3D shape models are naturally parameterized using vertices and faces, \ie, composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generative tasks using convolutional neural networks focus on a voxelized representation of the object. Lifting convolution operators from the traditional 2D to 3D results in high computational overhead with little additional benefit as most of the geometry information is contained on the surface boundary. Here we study the problem of directly generating the 3D shape surface of rigid and non-rigid shapes using deep convolutional neural networks. We develop a procedure to create consistent `geometry images' representing the shape surface of a category of 3D objects. We then use this consistent representation for category-specific shape surface generation from a parametric representation or an image by developing novel extensions of deep residual networks for the task of geometry image generation. Our experiments indicate that our network learns a meaningful representation of shape surfaces allowing it to interpolate between shape orientations and poses, invent new shape surfaces and reconstruct 3D shape surfaces from previously unseen images.
We introduce a data-driven approach to complete partial 3D shapes through a combination of volumetric deep neural networks and 3D shape synthesis. From a partially-scanned input shape, our method first infers a low-resolution -- but complete -- output. To this end, we introduce a 3D-Encoder-Predictor Network (3D-EPN) which is composed of 3D convolutional layers. The network is trained to predict and fill in missing data, and operates on an implicit surface representation that encodes both known and unknown space. This allows us to predict global structure in unknown areas at high accuracy. We then correlate these intermediary results with 3D geometry from a shape database at test time. In a final pass, we propose a patch-based 3D shape synthesis method that imposes the 3D geometry from these retrieved shapes as constraints on the coarsely-completed mesh. This synthesis process enables us to reconstruct fine-scale detail and generate high-resolution output while respecting the global mesh structure obtained by the 3D-EPN. Although our 3D-EPN outperforms state-of-the-art completion method, the main contribution in our work lies in the combination of a data-driven shape predictor and analytic 3D shape synthesis. In our results, we show extensive evaluations on a newly-introduced shape completion benchmark for both real-world and synthetic data.
We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion. Through the use of skip-connections, our model can successfully learn and infer a latent, hierarchical representation of objects. Furthermore, realistic 3D objects can be easily generated by sampling the VSL's latent probabilistic manifold. We show that our generative model can be trained end-to-end from 2D images to perform single image 3D model retrieval. Experiments show, both quantitatively and qualitatively, the improved generalization of our proposed model over a range of tasks, performing better or comparable to various state-of-the-art alternatives.
This paper introduces a 3D shape generative model based on deep neural networks. A new image-like (i.e., tensor) data representation for genus-zero 3D shapes is devised. It is based on the observation that complicated shapes can be well represented by multiple parameterizations (charts), each focusing on a different part of the shape. The new tensor data representation is used as input to Generative Adversarial Networks for the task of 3D shape generation. The 3D shape tensor representation is based on a multi-chart structure that enjoys a shape covering property and scale-translation rigidity. Scale-translation rigidity facilitates high quality 3D shape learning and guarantees unique reconstruction. The multi-chart structure uses as input a dataset of 3D shapes (with arbitrary connectivity) and a sparse correspondence between them. The output of our algorithm is a generative model that learns the shape distribution and is able to generate novel shapes, interpolate shapes, and explore the generated shape space. The effectiveness of the method is demonstrated for the task of anatomic shape generation including human body and bone (teeth) shape generation.
이미지-투-3D 형상 생성에 특화된 Diffusion Transformer(DiT) 압축 프레임워크를 제안하며, 레이어별 기여도를 Earth Mover's Distance(EMD)로 측정하는 활성도(vitality) 분석을 기반으로 구조적 가지치기(pruning), 적응형 양자화(quantization), 선택적 파인튜닝을 결합한다. Step1X-3D, Hunyuan3D 2.0 등 최신 모델에 적용하여 최대 66%의 모델 크기 감소를 달성하면서도 원본 수준의 기하학적 충실도를 유지함을 실험으로 검증했다.
우리는 식물학적 나무와 식물과 같이 3D 기하학과 분지 구조 모두에서 변형되는 복잡한 나무형 3D 객체를 분석하고 생성하기 위한 새로운 수학적 프레임워크를 제안한다. 기존 연구들이 나무형 객체의 골격(skeletal) 구조만 고려하거나 가지 두께를 이용해 3D 기하학을 근사하는 것과 달리, 제안된 프레임워크는 나무 가지의 3D 기하학과 그들이 상호 연결되는 방식을 모두 정확하게 모델링한다. 본 논문에서는 genus-0 표면의 통계 분석을 위해 최초로 제안된 Square Root Normal Fields(SRNF) 표현을 나무형 3D 객체로 일반화한다. 그다음 나무형 3D 객체를, 하나의 3D 나무형상을 다른 것과 정렬하기 위해 적용해야 하는 표면의 굽힘(bending)과 신장(stretching), 그리고 구조적 변화의 정도를 측정하는 새로운 리만(Riemannian) 메트릭을 갖춘 새로운 리만 나무형상 공간 위의 점으로 취급한다. 이를 통해 변형은 이 새로운 나무형상 공간에서의 궤적(trajectory)이 된다. 우리는 이 새로운 나무형상 공간과 해당 메트릭의 이론적 성질을 분석하고, 복잡한 3D 나무 사이의 점별(point-wise) 및 가지별(branch-wise) 대응(correspondence)과 측지선(geodesic) 경로를 계산하는 알고리즘을 개발한다. 마지막으로 이러한 구성 요소를 (1) 나무형 3D 객체 집합의 통계적 요약, 즉 평균(mean)과 변이 모드(mode of variation)를 계산하고, (2) 나무형 3D 객체 모집단에 적합한 확률 분포로부터 샘플링하여 새로운 나무형 3D 객체를 합성(synthesize)하는 데 사용하는 방법을 보인다. 실제 및 합성 식물과 식물학적 나무에 대해 제안된 프레임워크의 성능과 유용성을 시연하고, 최신 기법(state-of-the-art)을 크게 능가함을 보인다.
본 논문은 변형 형상 집합의 기저 연속 형상 공간을 학습하기 위한 잠재 확산 모델인 ARAPDiffusion을 제안한다. 핵심 혁신은 가능한 한 강체적(as-rigid-as-possible, ARAP) 변형 모델을 잠재 확산(LD)에 정규화 손실로 주입하여, 생성 모델 학습에 풍부한 3D 학습 데이터가 필요하다는 요구를 완화하는 데 있다. 표준 LD와 달리, ARAP 모델이 인코더/디코더와 LD 모델 모두를 개선하는 데 어떻게 활용될 수 있는지 보여준다. 학습 절차는 LD 모델이 정의한 합성 분포를 이용해 형상 인코더/디코더를 향상시키는 정규화 손실을 구성하는 단계와, 형상 디코더를 이용해 LD 모델을 개선하는 정규화 손실을 구성하는 단계를 교차한다. 또한 표현에 구애받지 않는 LD 과정과 비정렬(unorganized) 포인트 클라우드에 적용 가능한 암시적 형상 디코더를 결합하는 LD 패러다임의 이점을 보여준다. 비조건부 및 조건부 형상 생성 실험 결과는 ARAPDiffusion이 기준선 접근법 대비 갖는 장점을 입증한다.