Related papers: A Robust 3D-2D Interactive Tool for Scene Segmenta…
3D scene understanding has gained significant attention due to its wide range of applications. However, existing methods for 3D scene understanding are limited to specific downstream tasks, which hinders their practicality in real-world…
Present-day deep neural networks for video semantic segmentation require a large number of fine-grained pixel-level annotations to achieve the best possible results. Obtaining such annotations, however, is very expensive. On the other hand,…
Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a model for a single task with supervision. We propose OpenScene, an alternative approach where a model predicts dense features for 3D scene points that are…
Data annotation is crucial for developing machine learning solutions. The current paradigm is to hire ordinary human annotators to annotate data instructed by expert-crafted guidelines. As this paradigm is laborious, tedious, and costly, we…
We propose an approach for semi-automatic annotation of object instances. While most current methods treat object segmentation as a pixel-labeling problem, we here cast it as a polygon prediction task, mimicking how most current datasets…
We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation…
Given the prominence of current 3D sensors, a fine-grained analysis on the basic point cloud data is worthy of further investigation. Particularly, real point cloud scenes can intuitively capture complex surroundings in the real world, but…
The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part…
Pixelwise annotation of image sequences can be very tedious for humans. Interactive video object segmentation aims to utilize automatic methods to speed up the process and reduce the workload of the annotators. Most contemporary approaches…
We propose an efficient and scalable method for incrementally building a dense, semantically annotated 3D map in real-time. The proposed method assigns class probabilities to each region, not each element (e.g., surfel and voxel), of the 3D…
3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious. However, existing methods are usually complicated, e.g., pipelined training for 3D foreground/background segmentation,…
In the proposed study, we describe the possibility of automated dataset collection using an articulated robot. The proposed technology reduces the number of pixel errors on a polygonal dataset and the time spent on manual labeling of 2D…
Image collections, if critical aspects of image content are exposed, can spur research and practical applications in many domains. Supervised machine learning may be the only feasible way to annotate very large collections, but leading…
This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim…
3D functionality segmentation aims to identify the interactive element in a 3D scene required to perform an action described in free-form language (e.g., the handle to ``Open the second drawer of the cabinet near the bed''). Progress has…
Video Object Segmentation (VOS) is crucial for several applications, from video editing to video data generation. Training a VOS model requires an abundance of manually labeled training videos. The de-facto traditional way of annotating…
The existing image feature extraction methods are primarily based on the content and structure information of images, and rarely consider the contextual semantic information. Regarding some types of images such as scenes and objects, the…
3D semantic scene understanding is essential for digital twins, autonomous driving, smart agriculture, and embodied perception, yet dense point-wise annotation for point clouds remains expensive and difficult to scale. Existing…
Monocular 3D object detection (M3OD) is intrinsically ill-posed, hence training a high-performance deep learning based M3OD model requires a humongous amount of labeled data with complicated visual variation from diverse scenes, variety of…
Creating annotations for 3D medical data is time-consuming and often requires highly specialized expertise. Various tools have been implemented to aid this process. Segment Anything Model 2 (SAM 2) offers a general-purpose prompt-based…