Related papers: Structured3D: A Large Photo-realistic Dataset for …

We consider the problem of active 3D imaging using single-shot structured light systems, which are widely employed in commercial 3D sensing devices such as Apple Face ID and Intel RealSense. Traditional structured light methods typically…

Urban modeling is essential for city planning, scene synthesis, and gaming. Existing image-based methods generate diverse layouts but often lack geometric continuity and scalability, while graph-based methods capture structural relations…

Structured light (SL) systems acquire high-fidelity 3D geometry with active illumination projection. Conventional systems exhibit challenges when working in environments with strong ambient illumination, global illumination and cross-device…

Recent advancements in implicit 3D reconstruction methods, e.g., neural rendering fields and Gaussian splatting, have primarily focused on novel view synthesis of static or dynamic objects with continuous motion states. However, these…

The requirement of large amounts of annotated images has become one grand challenge while training deep neural network models for various visual detection and recognition tasks. This paper presents a novel image synthesis technique that…

Various datasets have been proposed for simultaneous localization and mapping (SLAM) and related problems. Existing datasets often include small environments, have incomplete ground truth, or lack important sensor data, such as depth and…

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…

We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the extreme viewpoint variation between aerial-ground image…

3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as immersive media, robotics, autonomous driving, and embodied AI. Early methods based on…

Real-life man-made objects often exhibit strong and easily-identifiable structure, as a direct result of their design or their intended functionality. Structure typically appears in the form of individual parts and their arrangement.…

We contribute the Habitat Synthetic Scene Dataset, a dataset of 211 high-quality 3D scenes, and use it to test navigation agent generalization to realistic 3D environments. Our dataset represents real interiors and contains a diverse set of…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Indoor 3D object detection is an essential task in single image scene understanding, impacting spatial cognition fundamentally in visual reasoning. Existing works on 3D object detection from a single image either pursue this goal through…

Understanding spatial relations (e.g., "laptop on table") in visual input is important for both humans and robots. Existing datasets are insufficient as they lack large-scale, high-quality 3D ground truth information, which is critical for…

As the intermediate-level representations bridging the two levels, structured representations of visual scenes, such as visual relationships between pairwise objects, have been shown to not only benefit compositional models in learning to…

In recent years, deep learning (DL) has shown great potential in the field of dermatological image analysis. However, existing datasets in this domain have significant limitations, including a small number of image samples, limited disease…

Real-world scenes, such as those in ScanNet, are difficult to capture, with highly limited data available. Generating realistic scenes with varied object poses remains an open and challenging task. In this work, we propose FactoredScenes, a…

Accurate and efficient object detection is crucial for safe and efficient operation of earth-moving equipment in mining. Traditional 2D image-based methods face limitations in dynamic and complex mine environments. To overcome these…

A vision model with general-purpose object-level 3D understanding should be capable of inferring both 2D (e.g., class name and bounding box) and 3D information (e.g., 3D location and 3D viewpoint) for arbitrary rigid objects in natural…

Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…