搜索结果：Removing

Towards intelligent image editing, object removal should eliminate both the target object and its causal visual artifacts, such as shadows and reflections. However, existing image appearance-based methods either follow strictly mask-aligned training and fail to remove these causal effects which are not explicitly masked, or adopt loosely mask-aligned strategies that lack controllability and may unintentionally over-erase other objects. We identify that these limitations stem from ignoring the causal relationship between an object's geometry presence and its visual effects. To address this limitation, we propose a geometry-aware two-stage framework that decouples object removal into (1) geometry removal and (2) appearance rendering. In the first stage, we remove the object directly from the geometry (e.g., depth) using strictly mask-aligned supervision, enabling structure-aware editing with strong geometric constraints. In the second stage, we render a photorealistic RGB image conditioned on the updated geometry, where causal visual effects are considered implicitly as a result of the modified 3D geometry. To guide learning in the geometry removal stage, we introduce a preference-dr

In this paper, we introduce a new perspective for improving image restoration by removing degradation in the textual representations of a given degraded image. Intuitively, restoration is much easier on text modality than image one. For example, it can be easily conducted by removing degradation-related words while keeping the content-aware words. Hence, we combine the advantages of images in detail description and ones of text in degradation removal to perform restoration. To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing the degradations, and then convert the restored textual representations into a guidance image for assisting image restoration. In particular, We ingeniously embed an image-to-text mapper and text restoration module into CLIP-equipped text-to-image models to generate the guidance. Then, we adopt a simple coarse-to-fine approach to dynamically inject multi-scale information from guidance to image restoration networks. Extensive experiments are conducted on various image restoration tasks, including deblurring, dehazing, deraining, and denoising, and all-in-one image restoration. The results showca

An initial procedure in text-as-data applications is text preprocessing. One of the typical steps, which can substantially facilitate computations, consists in removing infrequent words believed to provide limited information about the corpus. Despite popularity of vocabulary pruning, not many guidelines on how to implement it are available in the literature. The aim of the paper is to fill this gap by examining the effects of removing infrequent words for the quality of topics estimated using Latent Dirichlet Allocation. The analysis is based on Monte Carlo experiments taking into account different criteria for infrequent terms removal and various evaluation metrics. The results indicate that pruning is beneficial and that the share of vocabulary which might be eliminated can be quite considerable.

We show removability of half-line singularities for viscosity solutions of fully nonlinear elliptic PDEs which have classical density and a Jacobi inequality. An example of such a PDE is the Monge-Ampère equation, and the original proof follows from Caffarelli 1990. Other examples are the minimal surface and special Lagrangian equations. The present paper's quick doubling proof combines Savin's small perturbation theorem with the Jacobi inequality. The method more generally removes singularities satisfying the single side condition.

Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference of watermarks and restore the background content. However, existing methods often implement watermark component removal and background restoration tasks within a singular branch, leading to residual watermarks in the predictions and ignoring cases where watermarks heavily obscure the background. To address these limitations, this study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks and peripheral contextual information from unaffected regions. Moreover, a Global and Local Context Interaction module is built upon multi-layer perc

Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen domains. In this paper, we propose a new approach that aims to explicitly remove domain-specific features for domain generalization. Following this approach, we propose a novel framework called Learning and Removing Domain-specific features for Generalization (LRDG) that learns a domain-invariant model by tactically removing domain-specific features from the input images. Specifically, we design a classifier to effectively learn the domain-specific features for each source domain, respectively. We then develop an encoder-decoder network to map each input image into a new image space where the learned domain-specific features are removed. With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification. Extensive experiments demonstrate that our framework achieves superior performance compared with state-of-the-art methods.

We argue that it is the assumption of counterfactual definiteness and not locality or realism that results in Bell inequality violations. Furthermore, this assumption of counterfactual definiteness is not supported in classical mechanics. This means that the Bell inequality must fail classically, effectively removing the classical-quantum boundary, a conclusion prophesized by Bell himself. An implication here is that a local hidden variable theory, in the configuration space of classical mechanics cannot be ruled out. One very surprising result is that classical mechanics, in the context of Hamiltons stationary principle, may in fact have stronger correlations than quantum mechanics, in that it may be the key to beat Tsirelsons bound.

The effect of removing gamification elements from interactive systems has been a long-standing question in gamification research. Early work and foundational theories raised concerns about the endurance of positive effects and the emergence of negative ones. Yet, nearly a decade later, no work to date has sought consensus on these matters. Here, I offer a rapid review on the state of the art and what is known about the impact of removing gamification. A small corpus of 8 papers published between 2012 and 2020 were found. Findings suggest a mix of positive and negative effects related to removing gamification. Significantly, insufficient reporting, methodological weaknesses, limited measures, and superficial interpretations of "negative" results prevent firm conclusions. I offer a research agenda towards better understanding the nature of gamification removal. I end with a call for empirical and theoretical work on illuminating the effects that may linger after systems are un-gamified.

A fundamental challenge in networked systems is detection and removal of suspected malicious nodes. In reality, detection is always imperfect, and the decision about which potentially malicious nodes to remove must trade off false positives (erroneously removing benign nodes) and false negatives (mistakenly failing to remove malicious nodes). However, in network settings this conventional tradeoff must now account for node connectivity. In particular, malicious nodes may exert malicious influence, so that mistakenly leaving some of these in the network may cause damage to spread. On the other hand, removing benign nodes causes direct harm to these, and indirect harm to their benign neighbors who would wish to communicate with them. We formalize the problem of removing potentially malicious nodes from a network under uncertainty through an objective that takes connectivity into account. We show that optimally solving the resulting problem is NP-Hard. We then propose a tractable solution approach based on a convex relaxation of the objective. Finally, we experimentally demonstrate that our approach significantly outperforms both a simple baseline that ignores network structure, as we

Removing suspended solids and colloids are one of the most important water treatment processes. In this research, experimental tests have been done to assess the effects of pH and different doses of PACL on turbidity removal efficiency. The optimum dose of poly aluminum chloride (PACL) for removing turbidity was also determined. Turbidity was created artificially by adding the Kaolin with six different initial turbidities between 20 to 300 NTU rested for half an hour. The results have been showed that the best removal efficiency was at the pH of natural water. The optimal doses consumption of PACL was about 5 PPM.

In this paper we consider imprecise terrains, that is, triangulated terrains with a vertical error interval in the vertices. In particular, we study the problem of removing as many local extrema (minima and maxima) as possible from the terrain. We show that removing only minima or only maxima can be done optimally in O(n log n) time, for a terrain with n vertices. Interestingly, however, removing both the minima and maxima simultaneously is NP-hard, and is even hard to approximate within a factor of O(log log n) unless P=NP. Moreover, we show that even a simplified version of the problem where vertices can have only two different heights is already NP-hard, a result we obtain by proving hardness of a special case of 2-Disjoint Connected Subgraphs, a problem that has lately received considerable attention from the graph-algorithms community.

Indyk and Sidiropoulos (2007) proved that any orientable graph of genus $g$ can be probabilistically embedded into a graph of genus $g-1$ with constant distortion. Viewing a graph of genus $g$ as embedded on the surface of a sphere with $g$ handles attached, Indyk and Sidiropoulos' method gives an embedding into a distribution over planar graphs with distortion $2^{O(g)}$, by iteratively removing the handles. By removing all $g$ handles at once, we present a probabilistic embedding with distortion $O(g^2)$ for both orientable and non-orientable graphs. Our result is obtained by showing that the nimum-cut graph of Erickson and Har Peled (2004) has low dilation, and then randomly cutting this graph out of the surface using the Peeling Lemma of Lee and Sidiropoulos (2009).