Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DNN)-based models still struggle with large-area watermarks and are overly dependent on the quality of watermark mask prediction. To overcome these challenges, we introduce a novel feature adapting framework that leverages the representation modeling capacity of a pre-trained image inpainting model. Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model. We establish a dual-branch system to capture and embed features from the residual background content, which are merged into intermediate features of the inpainting backbone model via gated feature fusion modules. Moreover, for relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process. This contributes to a visible image removal model which is insensitive to the quality of watermark mask during testing. Extensive experiments on both a large-scale synthesized dataset and a real-world dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods. The source code is available in the supplementary materials.

In this paper, we propose FakeRadar, a novel deepfake video detection framework designed to address the challenges of cross-domain generalization in real-world scenarios. Existing detection methods typically rely on manipulation-specific cues, performing well on known forgery types but exhibiting severe limitations against emerging manipulation techniques. This poor generalization stems from their inability to adapt effectively to unseen forgery patterns. To overcome this, we leverage large-scale pretrained models (e.g. CLIP) to proactively probe the feature space, explicitly highlighting distributional gaps between real videos, known forgeries, and unseen manipulations. Specifically, FakeRadar introduces Forgery Outlier Probing, which employs dynamic subcluster modeling and cluster-conditional outlier generation to synthesize outlier samples near boundaries of estimated subclusters, simulating novel forgery artifacts beyond known manipulation types. Additionally, we design Outlier-Guided Tri-Training, which optimizes the detector to distinguish real, fake, and outlier samples using proposed outlier-driven contrastive learning and outlier-conditioned cross-entropy losses. Experiments show that FakeRadar outperforms existing methods across various benchmark datasets for deepfake video detection, particularly in cross-domain evaluations, by handling the variety of emerging manipulation techniques.

Visible watermark removal is crucial for evaluating watermark robustness and advancing more resilient protection techniques. Current methods face challenges in real-world scenarios due to architectural constraints in multi-task frameworks and limited dataset diversity. To address these challenges, we first propose a novel two-stage framework, PatchWiper, consisting of an independent watermark segmentation network and a highly dynamic patch-wise restoration network. This framework decouples watermark localization from background restoration, allowing each network to focus on its designated task. Our restoration network dynamically generates unique parameters for each image patch, enabling fine-grained adaptation to different watermark distortions. Second, we construct the Pixabay Real-world Watermark Dataset (PRWD ), which incorporates diverse background images and over 1,000 distinct watermark types, providing a more comprehensive benchmark for evaluating watermark removal methods. Extensive experiments on PRWD, ILAW, and real-world testing images demonstrate our method's superior performance over existing approaches, particularly in handling complex real-world cases.

This paper aims to restore original background images in watermarked videos, overcoming challenges posed by traditional approaches that fail to handle the temporal dynamics and diverse watermark characteristics effectively. Our method introduces a unique framework that first "decouples" the extraction of prior knowledge-such as common-sense knowledge and residual background details-from the temporal modeling process, allowing for independent handling of background restoration and temporal consistency. Subsequently, it "couples" these extracted features by integrating them into the temporal modeling backbone of a video inpainting (VI) framework. This integration is facilitated by a specialized module, which includes an intrinsic background image prediction sub-module and a dual-branch frame embedding module, designed to reduce watermark interference and enhance the application of prior knowledge. Moreover, a frame-adaptive feature selection module dynamically adjusts the extraction of prior features based on the corruption level of each frame, ensuring their effective incorporation into the temporal processing. Extensive experiments on YouTube-VOS and DAVIS datasets validate our method's efficiency in watermark removal and background restoration, showing significant improvement over state-of-the-art techniques in visible image watermark removal, video restoration, and video inpainting.

Point-based interactive image segmentation can ease the burden of mask annotation in applications such as semantic segmentation and image editing. However, fully extracting the target mask with limited user inputs remains challenging. We introduce a novel method, Variance-Insensitive and Target-Preserving Mask Refinement to enhance segmentation quality with fewer user inputs. Regarding the last segmentation result as the initial mask, an iterative refinement process is commonly employed to continually enhance the initial mask. Nevertheless, conventional techniques suffer from sensitivity to the variance in the initial mask. To circumvent this problem, our proposed method incorporates a mask matching algorithm for ensuring consistent inferences from different types of initial masks. We also introduce a target-aware zooming algorithm to preserve object information during downsampling, balancing efficiency and accuracy. Experiments on GrabCut, Berkeley, SBD, and DAVIS datasets demonstrate our method's state-of-the-art performance in interactive image segmentation.

We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally differentially private algorithms require little trust but are (provably) limited in their utility. Centrally differentially private algorithms can allow significantly better utility but require a trusted curator. This gap has led to significant interest in the design and implementation of simple cryptographic primitives, that can allow central-like utility guarantees without having to trust a central server.

The NOAA-20 Ozone Mapping and Profiler Suite (OMPS) is the second OMPS flight unit in the US Joint Polar Satellite System (JPSS) program [1]. Flying on the NOAA-20 satellite, the OMPS extends the 40+-year total column ozone and ozone profile records to monitor ozone concentration in the Earth atmosphere. Recent studies have been conducted over a wide range of radiometric calibration and geolocation calibration areas to improve the quality of OMPS sensor data records. This study covers several topics, including the removal of a solar intrusion signal during science data collection, reduction of solar activity impact resulting from solar activities, update of geolocation accuracy via refinement of the instrument CCD spatial registration, and minimization of a misalignment at the edges of the sensor spatial field of view during Earth view measurements. The objective of this study is to improve OMPS instrument performance to OMPS users' expectations, and to advance the OMPS calibration accuracy of sensor data records above current product requirements [2], [3]. The solar intrusion correction improved local radiance retrieval accuracy 4% for the Nadir Profiler sensor, during science observations in the Northern hemisphere where solar zenith angle ranges from$60^{\circ}$to$88^{\circ}$. Solar model improvements achieve up to 1% better fidelity in irradiance measurements during solar observations. The calibrated CCD spatial registration minimizes the misalignment in the Nadir Mapper sensor spatial field of view in both cross track and along track measurements, and refines the geolocation accuracy to less than 5 km for the sensor's geolocation products that have a nominal spatial resolution of 50 km x 17 km.

The performance of on-orbit satellite microwave instrument noise equivalent differential temperature (NEDT) and Temperature Data Record (TDR) data is always critical for the broad user community in both environmental data record (EDR) product retrieval and numerical weather prediction applications. Based on intensive pre-launch and post-launch calibration studies [1]-[5], this study assesses the post-launch performance of Metop-C AMSU-A instrument noise and antenna temperature data since the launch. It also conducts the quality assessment of the AMSU-A data in comparison with radiative transfer model (RTM) simulations, legacy NOAA-18/19 and Metop-A/B AMSU-A observations, and NOAA-20 ATMS observations. Finally, this study addresses impact of polarization and wavelength inconsistency on AMSU-A antenna temperature differences against ATMS.