CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918151229276160 |
|---|---|
| author | Shin, Jisu Shaw, Richard Shin, Seunghyun Zhang, Zhensong Jeon, Hae-Gon Perez-Pellitero, Eduardo |
| author_facet | Shin, Jisu Shaw, Richard Shin, Seunghyun Zhang, Zhensong Jeon, Hae-Gon Perez-Pellitero, Eduardo |
| contents | Modern camera pipelines apply extensive on-device processing, such as exposure adjustment, white balance, and color correction, which, while beneficial individually, often introduce photometric inconsistencies across views. These appearance variations violate multi-view consistency and degrade novel view synthesis. Joint optimization of scene-specific representations and per-image appearance embeddings has been proposed to address this issue, but with increased computational complexity and slower training. In this work, we propose a generalizable, feed-forward approach that predicts spatially adaptive bilateral grids to correct photometric variations in a multi-view consistent manner. Our model processes hundreds of frames in a single step, enabling efficient large-scale harmonization, and seamlessly integrates into downstream 3D reconstruction models, providing cross-scene generalization without requiring scene-specific retraining. To overcome the lack of paired data, we employ a hybrid self-supervised rendering loss leveraging 3D foundation models, improving generalization to real-world variations. Extensive experiments show that our approach outperforms or matches the reconstruction quality of existing scene-specific optimization methods with appearance modeling, without significantly affecting the training time of baseline 3D models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15748 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction Shin, Jisu Shaw, Richard Shin, Seunghyun Zhang, Zhensong Jeon, Hae-Gon Perez-Pellitero, Eduardo Computer Vision and Pattern Recognition Modern camera pipelines apply extensive on-device processing, such as exposure adjustment, white balance, and color correction, which, while beneficial individually, often introduce photometric inconsistencies across views. These appearance variations violate multi-view consistency and degrade novel view synthesis. Joint optimization of scene-specific representations and per-image appearance embeddings has been proposed to address this issue, but with increased computational complexity and slower training. In this work, we propose a generalizable, feed-forward approach that predicts spatially adaptive bilateral grids to correct photometric variations in a multi-view consistent manner. Our model processes hundreds of frames in a single step, enabling efficient large-scale harmonization, and seamlessly integrates into downstream 3D reconstruction models, providing cross-scene generalization without requiring scene-specific retraining. To overcome the lack of paired data, we employ a hybrid self-supervised rendering loss leveraging 3D foundation models, improving generalization to real-world variations. Extensive experiments show that our approach outperforms or matches the reconstruction quality of existing scene-specific optimization methods with appearance modeling, without significantly affecting the training time of baseline 3D models. |
| title | CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.15748 |