skip to main content

Title: Rotationally-Consistent Novel View Synthesis for Humans
Human novel view synthesis aims to synthesize target views of a human subject given input images taken from one or more reference viewpoints. Despite significant advances in model-free novel view synthesis, existing methods present two major limitations when applied to complex shapes like humans. First, these methods mainly focus on simple and symmetric objects, e.g., cars and chairs, limiting their performances to fine-grained and asymmetric shapes. Second, existing methods cannot guarantee visual consistency across different adjacent views of the same object. To solve these problems, we present in this paper a learning framework for the novel view synthesis of human subjects, which explicitly enforces consistency across different generated views of the subject. Specifically, we introduce a novel multi-view supervision and an explicit rotational loss during the learning process, enabling the model to preserve detailed body parts and to achieve consistency between adjacent synthesized views. To show the superior performance of our approach, we present qualitative and quantitative results on the Multi-View Human Action (MVHA) dataset we collected (consisting of 3D human models animated with different Mocap sequences and captured from 54 different viewpoints), the Pose-Varying Human Model (PVHM) dataset, and ShapeNet. The qualitative and quantitative results demonstrate that our approach more » outperforms the state-of-the-art baselines in both per-view synthesis quality, and in preserving rotational consistency and complex shapes (e.g. fine-grained details, challenging poses) across multiple adjacent views in a variety of scenarios, for both humans and rigid objects. « less
Authors:
; ; ; ; ;
Award ID(s):
1816148
Publication Date:
NSF-PAR ID:
10301932
Journal Name:
MM '20: Proceedings of the 28th ACM International Conference on Multimedia
Page Range or eLocation-ID:
2308 to 2316
Sponsoring Org:
National Science Foundation
More Like this
  1. Vedaldi, Andrea ; Bischof, Horst ; Brox, Thomas ; Frahm, Jan-Michael (Ed.)
    Novel view video synthesis aims to synthesize novel viewpoints videos given input captures of a human performance taken from multiple reference viewpoints and over consecutive time steps. Despite great advances in model-free novel view synthesis, existing methods present three limitations when applied to complex and time-varying human performance. First, these methods (and related datasets) mainly consider simple and symmetric objects. Second, they do not enforce explicit consistency across generated views. Third, they focus on static and non-moving objects. The fine-grained details of a human subject can therefore suffer from inconsistencies when synthesized across different viewpoints or time steps. To tackle these challenges, we introduce a human-specific framework that employs a learned 3D-aware representation. Specifically, we first introduce a novel siamese network that employs a gating layer for better reconstruction of the latent volumetric representation and, consequently, final visual results. Moreover, features from consecutive time steps are shared inside the network to improve temporal consistency. Second, we introduce a novel loss to explicitly enforce consistency across generated views both in space and in time. Third, we present the Multi-View Human Action (MVHA) dataset, consisting of near 1200 synthetic human performance captured from 54 viewpoints. Experiments on the MVHA, Pose-Varying Human Modelmore »and ShapeNet datasets show that our method outperforms the state-of-the-art baselines both in view generation quality and spatio-temporal consistency.« less
  2. In computer vision, tracking humans across camera views remains challenging, especially for complex scenarios with frequent occlusions, significant lighting changes and other difficulties. Under such conditions, most existing appearance and geometric cues are not reliable enough to distinguish humans across camera views. To address these challenges, this paper presents a stochastic attribute grammar model for leveraging complementary and discriminative human attributes for enhancing cross-view tracking. The key idea of our method is to introduce a hierarchical representation, parse graph, to describe a subject and its movement trajectory in both space and time domains. This results in a hierarchical compositional representation, comprising trajectory entities of varying level, including human boxes, 3D human boxes, tracklets and trajectories. We use a set of grammar rules to decompose a graph node (e.g. tracklet) into a set of children nodes (e.g. 3D human boxes), and augment each node with a set of attributes, including geometry (e.g., moving speed, direction), accessories (e.g., bags), and/or activities (e.g., walking, running). These attributes serve as valuable cues, in addition to appearance features (e.g., colors), in determining the associations of human detection boxes across cameras. In particular, the attributes of a parent node are inherited by its children nodes, resultingmore »in consistency constraints over the feasible parse graph. Thus, we cast cross-view human tracking as finding the most discriminative parse graph for each subject in videos. We develop a learning method to train this attribute grammar model from weakly supervised training data. To infer the optimal parse graph and its attributes, we develop an alternative parsing method that employs both top-down and bottom-up computations to search the optimal solution. We also explicitly reason the occlusion status of each entity in order to deal with significant changes of camera viewpoints. We evaluate the proposed method over public video benchmarks and demonstrate with extensive experiments that our method clearly outperforms state-of-theart tracking methods.« less
  3. We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. Previous work on learning shape reconstruction from multiple views uses discrete representations such as point clouds or voxels, while continuous surface generation approaches lack multi-view consistency. We address these issues by designing neural networks capable of generating high-quality parametric 3D surfaces which are also consistent between views. Furthermore, the generated 3D surfaces preserve accurate image pixel to 3D surface point correspondences, allowing us to lift texture information to reconstruct shapes with rich geometry and appearance. Our method is supervised and trained on a public dataset of shapes from common object categories. Quantitative results indicate that our method significantly outperforms previous work, while qualitative results demonstrate the high quality of our reconstructions.
  4. We present a new weakly supervised learning-based method for generating novel category-specific 3D shapes from unoccluded image collections. Our method is weakly supervised and only requires silhouette annotations from unoccluded, category-specific objects. Our method does not require access to the object's 3D shape, multiple observations per object from different views, intra-image pixel correspondences, or any view annotations. Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes. This is achieved through multiple discriminators that encode the distribution of 2D projections of the 3D shapes seen from a different views. Additionally, to determine the view information for each silhouette image, we also train a view prediction network on visualizations of 3D shapes synthesized by the generator. We iteratively alternate between training the generator and training the view prediction network. We validate our multi-projection GAN on both synthetic and real image datasets. Furthermore, we also show that multi-projection GANs can aid in learning other high-dimensional distributions from lower dimensional training datasets, such as material-class specific spatially varying reflectance properties from images.
  5. In order for robots to operate effectively in homes and workplaces, they must be able to manipulate the articulated objects common within environments built for and by humans. Kinematic models provide a concise representation of these objects that enable deliberate, generalizable manipulation policies. However, existing approaches to learning these models rely upon visual observations of an object’s motion, and are subject to the effects of occlusions and feature sparsity. Natural language descriptions provide a flexible and efficient means by which humans can provide complementary information in a weakly supervised manner suitable for a variety of different interactions (e.g., demonstrations and remote manipulation). In this paper, we present a multimodal learning framework that incorporates both vision and language information acquired in situ to estimate the structure and parameters that de- fine kinematic models of articulated objects. The visual signal takes the form of an RGB-D image stream that opportunistically captures object motion in an unprepared scene. Accompanying natural language descriptions of the motion constitute the linguistic signal. We model linguistic information using a probabilistic graphical model that grounds natural language descriptions to their referent kinematic motion. By exploiting the complementary nature of the vision and language observations, our method infers correctmore »kinematic models for various multiple-part objects on which the previous state-of-the- art, visual-only system fails. We evaluate our multimodal learning framework on a dataset comprised of a variety of household objects, and demonstrate a 23% improvement in model accuracy over the vision-only baseline.« less