Related papers: DISC: Dense Integrated Semantic Context for Large-…

OCR-based image captioning is an important but under-explored task, aiming to generate descriptions containing visual objects and scene text. Recent studies have made encouraging progress, but they are still suffering from a lack of overall…

Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision…

In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods…

Monocular depth estimation and semantic segmentation are two fundamental goals of scene understanding. Due to the advantages of task interaction, many works study the joint task learning algorithm. However, most existing methods fail to…

Autonomous mobile robots deployed in urban environments must be context-aware, i.e., able to distinguish between different semantic entities, and robust to occlusions. Current approaches like semantic scene completion (SSC) require…

Camera-based Semantic Scene Completion (SSC) is gaining attentions in the 3D perception field. However, properties such as perspective and occlusion lead to the underestimation of the geometry in distant regions, posing a critical issue for…

Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for…

Video semantic segmentation(VSS) has been widely employed in lots of fields, such as simultaneous localization and mapping, autonomous driving and surveillance. Its core challenge is how to leverage temporal information to achieve better…

In this paper, we propose ReSeg-CLIP, a new training-free Open-Vocabulary Semantic Segmentation method for remote sensing data. To compensate for the problems of vision language models, such as CLIP in semantic segmentation caused by…

Establishing dense correspondence across 3D shapes is crucial for fundamental downstream tasks, including texture transfer, shape interpolation, and robotic manipulation. However, learning these mappings without manual supervision remains a…

Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes. This paper presents ContextSeg - a simple yet highly effective approach to…

For applications such as autonomous driving, self-localization/camera pose estimation and scene parsing are crucial technologies. In this paper, we propose a unified framework to tackle these two problems simultaneously. The uniqueness of…

Contemporary transfer learning-based methods to alleviate the data insufficiency in change detection (CD) are mainly based on ImageNet pre-training. Self-supervised learning (SSL) has recently been introduced to remote sensing (RS) for…

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…

Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in…

Semantic scene completion, also known as semantic occupancy prediction, can provide dense geometric and semantic information for autonomous vehicles, which attracts the increasing attention of both academia and industry. Unfortunately,…

Semantic compression, a compression scheme where the distortion metric, typically MSE, is replaced with semantic fidelity metrics, tends to become more and more popular. Most recent semantic compression schemes rely on the foundation model…

The training of large multimodal models fundamentally relies on massive image-text datasets, which inevitably incur prohibitive computational overhead. Dataset selection offers a promising paradigm by identifying a highly informative…

High-quality training data are not always available in dynamic MRI. To address this, we propose a self-supervised deep learning method called deep image prior with structured sparsity (DISCUS) for reconstructing dynamic images. DISCUS is…

This work addresses a gap in semantic scene completion (SSC) data by creating a novel outdoor data set with accurate and complete dynamic scenes. Our data set is formed from randomly sampled views of the world at each time step, which…