Related papers: Evaluating Continual Learning Algorithms by Genera…

Continual learning is an online paradigm where a learner continually accumulates knowledge from different tasks encountered over sequential time steps. Importantly, the learner is required to extend and update its knowledge without…

Generating high-quality, textured 3D scenes from a single image remains a fundamental challenge in vision and graphics. Recent image-to-3D generators recover reasonable geometry from single views, but their object-centric training limits…

Recent conditional image synthesis approaches provide high-quality synthesized images. However, it is still challenging to accurately adjust image contents such as the positions and orientations of objects, and synthesized images often have…

For robots to perform assistive tasks in unstructured home environments, they must learn and reason on the semantic knowledge of the environments. Despite a resurgence in the development of semantic reasoning architectures, these methods…

Humans possess a remarkable ability to mentally explore and replay 3D environments they have previously experienced. Inspired by this mental process, we present EvoWorld: a world model that bridges panoramic video generation with evolving…

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

Despite groundbreaking progress in reinforcement learning for robotics, gameplay, and other complex domains, major challenges remain in applying reinforcement learning to the evolving, open-world problems often found in critical application…

In this paper, we propose Text2Scene, a model that generates various forms of compositional scene representations from natural language descriptions. Unlike recent works, our method does NOT use Generative Adversarial Networks (GANs).…

Realistic simulation is critical for applications ranging from robotics to animation. Traditional analytic simulators sometimes struggle to capture sufficiently realistic simulation which can lead to problems including the well known…

We present a deep generative scene modeling technique for indoor environments. Our goal is to train a generative model using a feed-forward neural network that maps a prior distribution (e.g., a normal distribution) to the distribution of…

Generating 3D worlds from text is a highly anticipated goal in computer vision. Existing works are limited by the degree of exploration they allow inside of a scene, i.e., produce streched-out and noisy artifacts when moving beyond central…

Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus on character consistency, they often overlook the crucial…

Generating high-fidelity 3D indoor scenes remains a significant challenge due to data scarcity and the complexity of modeling intricate spatial relations. Current methods often struggle to scale beyond training distribution to dense scenes…

Scene graph generation (SGG) endeavors to predict visual relationships between pairs of objects within an image. Prevailing SGG methods traditionally assume a one-off learning process for SGG. This conventional paradigm may necessitate…

In order to operate autonomously, a robot should explore the environment and build a model of each of the surrounding objects. A common approach is to carefully scan the whole workspace. This is time-consuming. It is also often impossible…

Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these…

Deep learning techniques have become one of the main propellers for solving engineering problems effectively and efficiently. For instance, Predictive Maintenance methods have been used to improve predictions of when maintenance is needed…

The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual…

Video generation has achieved impressive quality, but it still suffers from artifacts such as temporal inconsistency and violation of physical laws. Leveraging 3D scenes can fundamentally resolve these issues by providing precise control…

Hyperparameter selection in continual learning scenarios is a challenging and underexplored aspect, especially in practical non-stationary environments. Traditional approaches, such as grid searches with held-out validation data from all…