Related papers: Smartphone scene generator for efficient character…
We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes. More specifically, the input layout consists of one or more…
Visual scene understanding is a fundamental task in computer vision that aims to extract meaningful information from visual data. It traditionally involves disjoint and specialized algorithms for different tasks that are tailored for…
We present a method for creating 3D indoor scenes with a generative model learned from a collection of semantic-segmented depth images captured from different unknown scenes. Given a room with a specified size, our method automatically…
Generating realistic images from scene graphs asks neural networks to be able to reason about object relationships and compositionality. As a relatively new task, how to properly ensure the generated images comply with scene graphs or how…
We introduce Infinigen Indoors, a Blender-based procedural generator of photorealistic indoor scenes. It builds upon the existing Infinigen system, which focuses on natural scenes, but expands its coverage to indoor scenes by introducing a…
Training embodied agents in simulation has become mainstream for the embodied AI community. However, these agents often struggle when deployed in the physical world due to their inability to generalize to real-world environments. In this…
Object recognition and object pose estimation in robotic grasping continue to be significant challenges, since building a labelled dataset can be time consuming and financially costly in terms of data collection and annotation. In this…
Many top-performing image captioning models rely solely on object features computed with an object detection model to generate image descriptions. However, recent studies propose to directly use scene graphs to introduce information about…
Scene text image super-resolution has significantly improved the accuracy of scene text recognition. However, many existing methods emphasize performance over efficiency and ignore the practical need for lightweight solutions in deployment…
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…
3D Content Generation is at the heart of many computer graphics applications, including video gaming, film-making, virtual and augmented reality, etc. This paper proposes a novel deep-learning based approach for automatically generating…
Visual Commonsense Reasoning, which is regarded as one challenging task to pursue advanced visual scene comprehension, has been used to diagnose the reasoning ability of AI systems. However, reliable reasoning requires a good grasp of the…
3D semantic scene graphs are a powerful holistic representation as they describe the individual objects and depict the relation between them. They are compact high-level graphs that enable many tasks requiring scene reasoning. In real-world…
Careful robot manipulation in every-day cluttered environments requires an accurate understanding of the 3D scene, in order to grasp and place objects stably and reliably and to avoid colliding with other objects. In general, we must…
Little publicly available data exists for polarimetric measurements. When designing task specific polarimetric systems, the statistical properties of the task specific data becomes important. Until better polarimetric datasets are available…
This paper proposes an algorithm that turns a regular video capturing urban scenes into a high-quality endless animation, known as a Cinemagraph. The creation of a Cinemagraph usually requires a static camera in a carefully configured…
Identifying independently moving objects is an essential task for dynamic scene understanding. However, traditional cameras used in dynamic scenes may suffer from motion blur or exposure artifacts due to their sampling principle. By…
Scene understanding plays an important role in several high-level computer vision applications, such as autonomous vehicles, intelligent video surveillance, or robotics. However, too few solutions have been proposed for indoor/outdoor scene…
Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While recent approaches have…
Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing all occluded surfaces. While much progress has been made on…