Search

In this paper, we investigate the use of large multimodal models (LMMs) for generating virtual activities, leveraging the integration of vision-language modalities to enable the interpretation of virtual environments. This approach not only facilitates the recognition of scene layouts, semantic contexts, and object identities, but also empowers LMMs to abstract the elements of a scene. By correlating these abstractions with massive knowledge about human activities, LMMs are capable of generating adaptive and contextually relevant virtual activities. We propose a structured framework for articulating abstract activity descriptions, with an emphasis on delineating character interactions within the virtual milieu. Utilizing the derived high-level contexts, our methodology proficiently positions virtual characters, ensuring that their interactions and behaviors are realistically and contextually congruent through strategic optimizations. The implications of our findings are significant, offering a novel pathway for enhancing the realism and contextual appropriateness of virtual activities in simulated environments.

Scene Rearrangement Planning (SRP) is an interior task proposed recently. The previous work defines the action space of this task with handcrafted coarse-grained actions that are inflexible to be used for transforming scene arrangement and intractable to be deployed in practice. Additionally, this new task lacks realistic indoor scene rearrangement data to feed popular data-hungry learning approaches and meet the needs of quantitative evaluation. To address these problems, we propose a fine-grained action definition for SRP and introduce a large-scale scene rearrangement dataset. We also propose a novel learning paradigm to efficiently train an agent through self-playing, without any prior knowledge. The agent trained via our paradigm achieves superior performance on the introduced dataset compared to the baseline agents. We provide a detailed analysis of the design of our approach in our experiments., Comment: 7 pages, 4 figures

When the human-robot interactions become ubiquitous, the environment surrounding these interactions will have significant impact on the safety and comfort of the human and the effectiveness and efficiency of the robot. Although most robots are designed to work in the spaces created for humans, many environments, such as living rooms and offices, can be and should be redesigned to enhance and improve human-robot collaboration and interactions. This work uses autonomous wheelchair as an example and investigates the computational design in the human-robot coexistence spaces. Given the room size and the objects $O$ in the room, the proposed framework computes the optimal layouts of $O$ that satisfy both human preferences and navigation constraints of the wheelchair. The key enabling technique is a motion planner that can efficiently evaluate hundreds of similar motion planning problems. Our implementation shows that the proposed framework can produce a design around three to five minutes on average comparing to 10 to 20 minutes without the proposed motion planner. Our results also show that the proposed method produces reasonable designs even for tight spaces and for users with different preferences.

The arrangement of objects into a layout can be challenging for non-experts, as is affirmed by the existence of interior design professionals. Recent research into the automation of this task has yielded methods that can synthesize layouts of objects respecting aesthetic and functional constraints that are non-linear and competing. These methods usually adopt a stochastic optimization scheme, which samples from different layout configurations, a process that is slow and inefficient. We introduce an physics-motivated, continuous layout synthesis technique, which results in a significant gain in speed and is readily scalable. We demonstrate our method on a variety of examples and show that it achieves results similar to conventional layout synthesis based on Markov chain Monte Carlo (McMC) state-search, but is faster by at least an order of magnitude and can handle layouts of unprecedented size as well as tightly-packed layouts that can overwhelm McMC., Comment: 13 pages

Synthesizing 3D faces that give certain personality impressions is commonly needed in computer games, animations, and virtual world applications for producing realistic virtual characters. In this paper, we propose a novel approach to synthesize 3D faces based on personality impression for creating virtual characters. Our approach consists of two major steps. In the first step, we train classifiers using deep convolutional neural networks on a dataset of images with personality impression annotations, which are capable of predicting the personality impression of a face. In the second step, given a 3D face and a desired personality impression type as user inputs, our approach optimizes the facial details against the trained classifiers, so as to synthesize a face which gives the desired personality impression. We demonstrate our approach for synthesizing 3D faces giving desired personality impressions on a variety of 3D face models. Perceptual studies show that the perceived personality impressions of the synthesized faces agree with the target personality impressions specified for synthesizing the faces. Please refer to the supplementary materials for all results., Comment: 8pages;6 figures

Wayfinding signs play an important role in guiding users to navigate in a virtual environment and in helping pedestrians to find their ways in a real-world architectural site. Conventionally, the wayfinding design of a virtual environment is created manually, so as the wayfinding design of a real-world architectural site. The many possible navigation scenarios, as well as the interplay between signs and human navigation, can make the manual design process overwhelming and non-trivial. As a result, creating a wayfinding design for a typical layout can take months to several years. In this paper, we introduce the Way to Go! approach for automatically generating a wayfinding design for a given layout. The designer simply has to specify some navigation scenarios; our approach will automatically generate an optimized wayfinding design with signs properly placed considering human agents' visibility and possibility of making mistakes during a navigation. We demonstrate the effectiveness of our approach in generating wayfinding designs for different layouts such as a train station, a downtown and a canyon. We evaluate our results by comparing different wayfinding designs and show that our optimized wayfinding design can guide pedestrians to their destinations effectively and efficiently. Our approach can also help the designer visualize the accessibility of a destination from different locations, and correct any "blind zone" with additional signs.

We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms. In particular, we devise a learning-based pipeline of algorithms capable of automatically generating and rendering a potentially infinite variety of indoor scenes by using a stochastic grammar, represented as an attributed Spatial And-Or Graph, in conjunction with state-of-the-art physics-based rendering. Our pipeline is capable of synthesizing scene layouts with high diversity, and it is configurable inasmuch as it enables the precise customization and control of important attributes of the generated scenes. It renders photorealistic RGB images of the generated scenes while automatically synthesizing detailed, per-pixel ground truth data, including visible surface depth and normal, object identity, and material information (detailed to object parts), as well as environments (e.g., illuminations and camera viewpoints). We demonstrate the value of our synthesized dataset, by improving performance in certain machine-learning-based scene understanding tasks--depth and surface normal prediction, semantic segmentation, reconstruction, etc.--and by providing benchmarks for and diagnostics of trained models by modifying object attributes and scene properties in a controllable manner., Comment: Accepted in IJCV 2018

Recent advances of 3D acquisition devices have enabled large-scale acquisition of 3D scene data. Such data, if completely and well annotated, can serve as useful ingredients for a wide spectrum of computer vision and graphics works such as data-driven modeling and scene understanding, object detection and recognition. However, annotating a vast amount of 3D scene data remains challenging due to the lack of an effective tool and/or the complexity of 3D scenes (e.g. clutter, varying illumination conditions). This paper aims to build a robust annotation tool that effectively and conveniently enables the segmentation and annotation of massive 3D data. Our tool works by coupling 2D and 3D information via an interactive framework, through which users can provide high-level semantic annotation for objects. We have experimented our tool and found that a typical indoor scene could be well segmented and annotated in less than 30 minutes by using the tool, as opposed to a few hours if done manually. Along with the tool, we created a dataset of over a hundred 3D scenes associated with complete annotations using our tool. The tool and dataset are available at www.scenenn.net., Comment: 14 pages