Related papers: PRISM: Progressive Restoration for Scene Graph-bas…
In computer graphics and vision, recovering easily modifiable scene appearance from image data is crucial for applications such as content creation. We introduce a novel method that integrates 3D Gaussian Splatting with an implicit surface…
Recent advances in 3D foundation models have led to growing interest in reconstructing humans and their surrounding environments. However, most existing approaches focus on monocular inputs, and extending them to multi-view settings…
In recent years, Deep Neural Networks (DNN) have emerged as a practical method for image recognition. The raw data, which contain sensitive information, are generally exploited within the training process. However, when the training process…
Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this…
Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from…
Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle…
Robotic grasping in scenes with transparent and specular objects presents great challenges for methods relying on accurate depth information. In this paper, we introduce NeuGrasp, a neural surface reconstruction method that leverages…
Neural Radiance Field~(NeRF) achieves extremely high quality in object-scaled and indoor scene reconstruction. However, there exist some challenges when reconstructing large-scale scenes. MLP-based NeRFs suffer from limited network…
Interpreting the decision-making process of deep convolutional neural networks remains a central challenge in achieving trustworthy and transparent artificial intelligence. Explainable AI (XAI) techniques, particularly Class Activation Map…
As a common method in the field of computer vision, spatial attention mechanism has been widely used in semantic segmentation of remote sensing images due to its outstanding long-range dependency modeling capability. However, remote sensing…
Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over-smoothed scene…
Deep Learning has revolutionized machine learning, reaching unprecedented levels of accuracy, but at the cost of reduced interpretability. Especially in image processing systems, deep networks transform local pixel information into more…
This paper represents a neat yet effective framework, named SemanticMIM, to integrate the advantages of masked image modeling (MIM) and contrastive learning (CL) for general visual representation. We conduct a thorough comparative analysis…
Reconstructing photo-realistic large-scale scenes from images, for example at city scale, is a long-standing problem in computer graphics. Neural rendering is an emerging technique that enables photo-realistic image synthesis from…
Recently, convolutional neural networks (CNN) have been successfully applied to many remote sensing problems. However, deep learning techniques for multi-image super-resolution from multitemporal unregistered imagery have received little…
Scene graphs (SGs) provide structured relational representations crucial for decoding complex, dynamic surgical environments. This PRISMA-ScR-guided scoping review systematically maps the evolving landscape of SG research in surgery,…
Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training…
This paper investigates an open research challenge of reconstructing high-quality, large 3D open scenes from images. It is observed existing methods have various limitations, such as requiring precise camera poses for input and dense…
Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character…
Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large language models (LLMs) for natural language processing (NLP),…