Related papers: Automatic dataset generation for specific object d…
Scene text detection techniques have garnered significant attention due to their wide-ranging applications. However, existing methods have a high demand for training data, and obtaining accurate human annotations is labor-intensive and…
The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video. We make four contributions: First, we introduce an object-centric segmentation model with a depth-ordered layer…
Main subjects usually exist in the images or videos, as they are the objects that the photographer wants to highlight. Human viewers can easily identify them but algorithms often confuse them with other objects. Detecting the main subjects…
Image generation models trained on large datasets can synthesize high-quality images but often produce spatially inconsistent and distorted images due to limited information about the underlying structures and spatial layouts. In this work,…
Passive methods for object detection and segmentation treat images of the same scene as individual samples and do not exploit object permanence across multiple views. Generalization to novel or difficult viewpoints thus requires additional…
Images of realistic scenes often contain intra-class objects that are heavily occluded from each other, making the amodal perception task that requires parsing the occluded parts of the objects challenging. Although important for downstream…
Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…
Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…
Accurate detection and tracking of objects is vital for effective video understanding. In previous work, the two tasks have been combined in a way that tracking is based heavily on detection, but the detection benefits marginally from the…
A fundamental task in detecting foreground objects in both static and dynamic scenes is to take the best choice of color system representation and the efficient technique for background modeling. We propose in this paper a non-parametric…
In computer vision, object detection is an important task that finds its application in many scenarios. However, obtaining extensive labels can be challenging, especially in crowded scenes. Recently, the Segment Anything Model (SAM) has…
Collecting 3D object datasets involves a large amount of manual work and is time consuming. Getting complete models of objects either requires a 3D scanner that covers all the surfaces of an object or one needs to rotate it to completely…
This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…
Most currently used object detection methods are learning-based, and can detect objects under varying appearances. Those models require training and a training dataset. We focus on use cases with less data variation, but the requirement of…
Current methods aggregate multi-level features or introduce edge and skeleton to get more refined saliency maps. However, little attention is paid to how to obtain the complete salient object in cluttered background, where the targets are…
Manipulating images of complex scenes to reconstruct, insert and/or remove specific object instances is a challenging task. Complex scenes contain multiple semantics and objects, which are frequently cluttered or ambiguous, thus hampering…
Segmenting foreground object from a video is a challenging task because of the large deformations of the objects, occlusions, and background clutter. In this paper, we propose a frame-by-frame but computationally efficient approach for…
Synthesizing novel views for urban environments is crucial for tasks like autonomous driving and virtual tours. Compared to object-level or indoor situations, outdoor settings present unique challenges, such as inconsistency across frames…
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…
Indoor scene synthesis involves automatically picking and placing furniture appropriately on a floor plan, so that the scene looks realistic and is functionally plausible. Such scenes can serve as homes for immersive 3D experiences, or be…