CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction

TL;DR

This paper introduces CHROMA, a fast, generalizable method for multi-view appearance harmonization that corrects photometric inconsistencies across views using bilateral grid prediction, enhancing 3D reconstruction quality.

Contribution

CHROMA presents a novel, feed-forward approach predicting bilateral grids for multi-view consistency, enabling efficient large-scale harmonization without scene-specific retraining.

Findings

Outperforms scene-specific optimization methods in reconstruction quality

Processes hundreds of frames in a single step for efficiency

Improves generalization to real-world variations

Abstract

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.