Related papers: MeTACAST: Target- and Context-aware Spatial Select…
We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…
We present MetaSpatial, the first reinforcement learning (RL)-based framework designed to enhance 3D spatial reasoning in vision-language models (VLMs), enabling real-time 3D scene generation without the need for hard-coded optimizations.…
The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been…
We introduce PartSTAD, a method designed for the task adaptation of 2D-to-3D segmentation lifting. Recent studies have highlighted the advantages of utilizing 2D segmentation models to achieve high-quality 3D segmentation through few-shot…
Selection is the first step in many image editing processes, enabling faster and simpler modifications of all pixels sharing a common modality. In this work, we present a method for material selection in images, robust to lighting and…
Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention…
With the rapid development of measurement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning…
LiDAR-based localization approach is a fundamental module for large-scale navigation tasks, such as last-mile delivery and autonomous driving, and localization robustness highly relies on viewpoints and 3D feature extraction. Our previous…
Semantic segmentation is a fundamental task in computer vision, which can be considered as a per-pixel classification problem. Recently, although fully convolutional neural network (FCN) based approaches have made remarkable progress in…
The visualization of 3D point cloud data is essential in fields such as autonomous navigation, environmental monitoring, and disaster response, where tasks like object recognition, structural analysis, and spatiotemporal exploration rely on…
Features play an important role in various visual tasks, especially in visual place recognition applied in perceptual changing environments. In this paper, we address the challenges of place recognition due to dynamics and confusable…
Accurate localization in diverse environments is a fundamental challenge in computer vision and robotics. The task involves determining a sensor's precise position and orientation, typically a camera, within a given space. Traditional…
While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…
Concept personalization methods enable large text-to-image models to learn specific subjects (e.g., objects/poses/3D models) and synthesize renditions in new contexts. Given that the image references are highly biased towards visual…
Semantic segmentation and activity classification are key components to creating intelligent surgical systems able to understand and assist clinical workflow. In the Operating Room, semantic segmentation is at the core of creating robots…
As the demand for immersive 3D content grows, the need for intuitive and efficient interaction methods becomes paramount. Current techniques for physically manipulating 3D content within Virtual Reality (VR) often face significant…
The voluminous nature of geospatial temporal data from physical monitors and simulation models poses challenges to efficient data access, often resulting in cumbersome temporal selection experiences in web-based data portals. Thus,…
The reconstruction of textureless areas has long been a challenging problem in MVS due to lack of reliable pixel correspondences between images. In this paper, we propose the Textureless-aware Segmentation And Correlative Refinement guided…
3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.…
Fusion of 2D images and 3D point clouds is important because information from dense images can enhance sparse point clouds. However, fusion is challenging because 2D and 3D data live in different spaces. In this work, we propose MVPNet…