Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.20924 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917360450928640 |
|---|---|
| author | Jakubowska, Weronika Zieliński, Mikołaj Tobiasz, Rafał Byrski, Krzysztof Zięba, Maciej Belter, Dominik Spurek, Przemysław |
| author_facet | Jakubowska, Weronika Zieliński, Mikołaj Tobiasz, Rafał Byrski, Krzysztof Zięba, Maciej Belter, Dominik Spurek, Przemysław |
| contents | Implicit Neural Representations (INRs) are widely used for modeling continuous 2D images, enabling high-fidelity reconstruction, super-resolution, and compression. Architectures such as SIREN, WIRE, and FINER demonstrate their ability to capture fine image details. However, conventional INRs lack explicit geometric structure, limiting local editing, and integration with physical simulation. To address these limitations, we propose GaINeR (Geometry-Aware Implicit Neural Representation for Image Editing), a novel framework for 2D images that combines trainable Gaussian distributions with a neural network-based INR. For a given image coordinate, the model retrieves the K nearest Gaussians, aggregates distance-weighted embeddings, and predicts the RGB value via a neural network. This design enables continuous image representation, interpretable geometric structure, and flexible local editing, providing a foundation for physically aware and interactive image manipulation. Our method supports geometry-consistent transformations, seamless super-resolution, and integration with physics-based simulations. Moreover, the Gaussian representation allows lifting a single 2D image into a geometry-aware 3D representation, enabling depth-guided editing. Experiments demonstrate that GaINeR achieves state-of-the-art reconstruction quality while maintaining flexible and physically consistent image editing. The official implementation of our method is publicly available at https://github.com/WJakubowska/GaINeR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20924 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GaINeR: Geometry-Aware Implicit Network Representation Jakubowska, Weronika Zieliński, Mikołaj Tobiasz, Rafał Byrski, Krzysztof Zięba, Maciej Belter, Dominik Spurek, Przemysław Computer Vision and Pattern Recognition Implicit Neural Representations (INRs) are widely used for modeling continuous 2D images, enabling high-fidelity reconstruction, super-resolution, and compression. Architectures such as SIREN, WIRE, and FINER demonstrate their ability to capture fine image details. However, conventional INRs lack explicit geometric structure, limiting local editing, and integration with physical simulation. To address these limitations, we propose GaINeR (Geometry-Aware Implicit Neural Representation for Image Editing), a novel framework for 2D images that combines trainable Gaussian distributions with a neural network-based INR. For a given image coordinate, the model retrieves the K nearest Gaussians, aggregates distance-weighted embeddings, and predicts the RGB value via a neural network. This design enables continuous image representation, interpretable geometric structure, and flexible local editing, providing a foundation for physically aware and interactive image manipulation. Our method supports geometry-consistent transformations, seamless super-resolution, and integration with physics-based simulations. Moreover, the Gaussian representation allows lifting a single 2D image into a geometry-aware 3D representation, enabling depth-guided editing. Experiments demonstrate that GaINeR achieves state-of-the-art reconstruction quality while maintaining flexible and physically consistent image editing. The official implementation of our method is publicly available at https://github.com/WJakubowska/GaINeR. |
| title | GaINeR: Geometry-Aware Implicit Network Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.20924 |