Adjustable Visual Appearance for Generalizable Novel View Synthesis
This addresses the challenge of generating 3D consistent renderings with realistic appearance changes for applications in computer vision and graphics, representing an incremental advance in generalizable methods.
The paper tackles the problem of novel view synthesis with adjustable visual appearance, enabling rendered views to match target weather or lighting conditions without scene-specific training or reference views, and shows results through experiments on real and synthetic scenes.
We present a generalizable novel view synthesis method which enables modifying the visual appearance of an observed scene so rendered views match a target weather or lighting condition without any scene specific training or access to reference views at the target condition. Our method is based on a pretrained generalizable transformer architecture and is fine-tuned on synthetically generated scenes under different appearance conditions. This allows for rendering novel views in a consistent manner for 3D scenes that were not included in the training set, along with the ability to (i) modify their appearance to match the target condition and (ii) smoothly interpolate between different conditions. Experiments on real and synthetic scenes show that our method is able to generate 3D consistent renderings while making realistic appearance changes, including qualitative and quantitative comparisons. Please refer to our project page for video results: https://ava-nvs.github.io/