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

IEEE ICIP 2025 - The International Conference on Image Processing (ICIP), sponsored by the IEEE Signal Processing Society, is the premier forum for the presentation of technological advances and research results in the fields of theoretical, experimental, and applied image and video processing. ICIP has been held annually since 1994, brings together leading engineers and scientists in image and video processing from around the world. Visit the website.

In nighttime conditions, high noise levels and bright Illumination sources degrade image quality, making low-light image enhancement challenging. Thermal images provide complementary information, offering richer textures and structural details. We propose RT-X Net, a cross-attention network that fuses RGB and thermal images for nighttime image enhancement. We leverage self-attention networks for feature extraction and a cross-attention mechanism for fusion to effectively integrate information from both modalities.

Categories:
33 Views

The video represents the Sheep-Sculpture rendering at 360 degrees of view by the original 3DGS method from a dataset that contains the 16:40 and 17:27 time intervals images.

Categories:
19 Views

The video represents the Sheep-Sculpture rendering at 16:59 from 360 degrees of view by our time-dependent modeling method from a dataset that contains the 16:40 and 17:27 time intervals images.

Categories:
23 Views

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.

Categories:
16 Views

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.

Categories:
86 Views

Pages