LookCloser: Frequency-aware Radiance Field for Tiny-Detail Scene
This work addresses a limitation in immersive scene modeling for computer vision and graphics applications, offering an incremental improvement over existing NeRF methods.
The paper tackles the problem of balancing overall scene structure and fine details in neural radiance fields (NeRF) for view synthesis, introducing FA-NeRF, which uses frequency-aware rendering to achieve state-of-the-art performance in modeling entire scenes while preserving high-definition details.
Humans perceive and comprehend their surroundings through information spanning multiple frequencies. In immersive scenes, people naturally scan their environment to grasp its overall structure while examining fine details of objects that capture their attention. However, current NeRF frameworks primarily focus on modeling either high-frequency local views or the broad structure of scenes with low-frequency information, which is limited to balancing both. We introduce FA-NeRF, a novel frequency-aware framework for view synthesis that simultaneously captures the overall scene structure and high-definition details within a single NeRF model. To achieve this, we propose a 3D frequency quantification method that analyzes the scene's frequency distribution, enabling frequency-aware rendering. Our framework incorporates a frequency grid for fast convergence and querying, a frequency-aware feature re-weighting strategy to balance features across different frequency contents. Extensive experiments show that our method significantly outperforms existing approaches in modeling entire scenes while preserving fine details. Project page: https://coscatter.github.io/LookCloser/