Sorry, you need to enable JavaScript to visit this website.

Copy Detection system aims to identify if a query image is an edited/manipulated copy of an image from a large reference database with millions of images. While global image descriptors can retrieve visually similar images, they struggle to differentiate near-duplicates from semantically similar instances. We propose a dual-triplet metric learning (DTML) technique to learn global image features that group near-duplicates closer than visually similar images while maintaining the semantic structure of the embedding space.

Supplementary Materials for "RETHINKING IMAGE HISTOGRAM MATCHING FOR IMAGE CLASSIFICATION" at ICIP2025.

Augmented reality (AR) provides ways to visualize missing view samples for novel view synthesis. Existing approaches present 3D annotations for new view samples and task users with taking images by aligning the AR display. This data collection task is known to be mentally demanding and limits capture areas to pre-defined small areas due to ideal but restrictive underlying sampling theory. To free users from 3D annotations and limited scene exploration, we propose using locally reconstructed light fields and visualizing errors to be removed by inserting new views.

Supplementary Materials for "WEAKLY SUPERVISED DEFECT LOCALIZATION WITH RESIDUAL FEATURES"

ICIP2025_1674_supplementary-material_Multi_Res_3DGS

Supplementary of IMPROVING OPEN-WORLD CLASS-AGNOSTIC OBJECT DETECTORS VIA FEATURE DISTILLATION WITH STUDENT-AWARE ADAPTATION

Supplementary Materials of "CURVE: CLIP-Utilized Reinforcement learning for Visual image Enhancement via Simple Image Processing" submitted to ICIP 2025

Transformers demonstrate competitive performance in terms of precision on the problem of vision-based object detection. However, they require considerable computational resources due to the quadratic size of the attention weights.

Video outpainting presents a unique challenge of extending the borders while maintaining consistency with the given content. In this paper, we suggest the use of video inpainting models that excel in object flow learning and reconstruction in outpainting rather than solely generating the background as in existing methods. However, directly applying or fine-tuning inpainting models to outpainting has shown to be ineffective, often leading to blurry results.

Collecting high quality data for object detection tasks is challenging due to the inherent subjectivity in labeling the boundaries of an object. This makes it difficult to not only collect consistent annotations across a dataset but also to validate them, as no two annotators are likely to label the same object using the exact same coordinates. These challenges are further compounded when object boundaries are partially visible or blurred, which can be the case in many domains.