Massive datasets and high-capacity models have driven many recent advancements in computer vision and natural language understanding. This work presents a platform to enable similar success stories in Embodied AI. We propose ProcTHOR, a framework for procedural generation of Embodied AI environments. ProcTHOR enables us to sample arbitrarily large datasets of diverse, interactive, customizable, and performant virtual environments to train and evaluate embodied agents across navigation, interaction, and manipulation tasks. We demonstrate the power and potential of ProcTHOR via a sample of 10,000 generated houses and a simple neural model. Models trained using only RGB images on ProcTHOR, with no explicit mapping and no human task supervision produce state-of-the-art results across 6 embodied AI benchmarks for navigation, rearrangement, and arm manipulation, including the presently running Habitat 2022, AI2-THOR Rearrangement 2022, and RoboTHOR challenges. We also demonstrate strong 0-shot results on these benchmarks, via pre-training on ProcTHOR with no fine-tuning on the downstream benchmark, often beating previous state-of-the-art systems that access the downstream training data.

ProcTHOR: Large-Scale Embodied AI Using Procedural Generation

Generating realistic 3D worlds occupied by moving humans has many applications in games, architecture, and synthetic data creation. But generating such scenes is expensive and labor intensive. Recent work generates human poses and motions given a 3D scene. Here, we take the opposite approach and generate 3D indoor scenes given 3D human motion. Such motions can come from archival motion capture or from IMU sensors worn on the body, effectively turning human movement in a"scanner"of the 3D world. Intuitively, human movement indicates the free-space in a room and human contact indicates surfaces or objects that support activities such as sitting, lying or touching. We propose MIME (Mining Interaction and Movement to infer 3D Environments), which is a generative model of indoor scenes that produces furniture layouts that are consistent with the human movement. MIME uses an auto-regressive transformer architecture that takes the already generated objects in the scene as well as the human motion as input, and outputs the next plausible object. To train MIME, we build a dataset by populating the 3D FRONT scene dataset with 3D humans. Our experiments show that MIME produces more diverse and plausible 3D scenes than a recent generative scene method that does not know about human movement. Code and data will be available for research at https://mime.is.tue.mpg.de.

MIME: Human-Aware 3D Scene Generation

The availability of rich 3D datasets corresponding to the geometrical complexity of the built environments is considered an ongoing challenge for 3D deep learning methodologies. To address this challenge, we introduce GenScan, a generative system that populates synthetic 3D scan datasets in a parametric fashion. The system takes an existing captured 3D scan as an input and outputs alternative variations of the building layout including walls, doors, and furniture with corresponding textures. GenScan is a fully automated system that can also be manually controlled by a user through an assigned user interface. Our proposed system utilizes a combination of a hybrid deep neural network and a parametrizer module to extract and transform elements of a given 3D scan. GenScan takes advantage of style transfer techniques to generate new textures for the generated scenes. We believe our system would facilitate data augmentation to expand the currently limited 3D geometry datasets commonly used in 3D computer vision, generative design, and general 3D deep learning tasks.

GenScan: A Generative Method for Populating Parametric 3D Scan Datasets.

Developing fully parametric building models for performance-based generative design tasks often requires proficiency in many advanced 3D modeling and visual programming, limiting its use for many building designers. Moreover, iterations of such models can be time-consuming tasks and sometimes limiting, as major changes in the layout design may result in remodeling the entire parametric definition. To address these challenges, we introduce a novel automated generative design system, which takes a basic floor plan sketch as an input and provides a parametric model prepared for multi-objective building optimization as output. Furthermore, the user-designer can assign various design variables for its desired building elements by using simple annotations in the drawing. The system would recognize the corresponding element and define variable constraints to prepare for a multi-objective optimization problem.

SketchOpt: Sketch-based Parametric Model Retrieval for Generative Design

Remote telepresence via next-generation mixed reality platforms can provide higher levels of immersion for computer-mediated communications, allowing participants to engage in a wide spectrum of activities, previously not possible in 2D screen-based communication methods. However, as mixed reality experiences are limited to the local physical surrounding of each user, finding a common virtual ground where users can freely move and interact with each other is challenging. In this paper, we propose a novel mutual scene synthesis method that takes the participants' spaces as input, and generates a virtual synthetic scene that corresponds to the functional features of all participants' local spaces. Our method combines a mutual function optimization module with a deep-learning conditional scene augmentation process to generate a scene mutually and physically accessible to all participants of a mixed reality telepresence scenario. The synthesized scene can hold mutual walkable, sittable and workable functions, all corresponding to physical objects in the users' real environments. We perform experiments using the MatterPort3D dataset and conduct comparative user studies to evaluate the effectiveness of our system. Our results show that our proposed approach can be a promising research direction for facilitating contextualized telepresence systems for next-generation spatial computing platforms.

Mutual Scene Synthesis for Mixed Reality Telepresence

Spatial computing experiences are constrained by the real-world surroundings of the user. In such experiences, augmenting virtual objects to existing scenes require a contextual approach, where geometrical conflicts are avoided, and functional and plausible relationships to other objects are maintained in the target environment. Yet, due to the complexity and diversity of user environments, automatically calculating ideal positions of virtual content that is adaptive to the context of the scene is considered a challenging task. Motivated by this problem, in this paper we introduce SceneGen, a generative contextual augmentation framework that predicts virtual object positions and orientations within existing scenes. SceneGen takes a semantically segmented scene as input, and outputs positional and orientational probability maps for placing virtual content. We formulate a novel spatial Scene Graph representation, which encapsulates explicit topological properties between objects, object groups, and the room. We believe providing explicit and intuitive features plays an important role in informative content creation and user interaction of spatial computing settings, a quality that is not captured in implicit models. We use kernel density estimation (KDE) to build a multivariate conditional knowledge model trained using prior spatial Scene Graphs extracted from real-world 3D scanned data. To further capture orientational properties, we develop a fast pose annotation tool to extend current real-world datasets with orientational labels. Finally, to demonstrate our system in action, we develop an Augmented Reality application, in which objects can be contextually augmented in real-time.

Melody Mao

Papers

SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors