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

ICLR 2026 Conference Submission9595 Authors

Keywords: Bilateral Grid, Appearance Harmonization, 3D Reconstruction

TL;DR: We propose a feed-forward method that harmonizes multi-view appearance using bilateral grid, generalizes across scenes without retraining, and matches or surpasses optimization-based methods without extra training cost.

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.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 9595