Geometry-Aware Scene Configurations for Novel View Synthesis
This work addresses the challenge of immersive view synthesis for indoor environments with irregular layouts, offering incremental improvements over existing scalable Neural Radiance Field representations.
The paper tackles the problem of efficiently generating novel views in complex indoor scenes from incomplete observations by proposing scene-adaptive strategies for resource allocation, resulting in significant enhancements in rendering quality and memory usage compared to baseline methods with regular placements.
We propose scene-adaptive strategies to efficiently allocate representation capacity for generating immersive experiences of indoor environments from incomplete observations. Indoor scenes with multiple rooms often exhibit irregular layouts with varying complexity, containing clutter, occlusion, and flat walls. We maximize the utilization of limited resources with guidance from geometric priors, which are often readily available after pre-processing stages. We record observation statistics on the estimated geometric scaffold and guide the optimal placement of bases, which greatly improves upon the uniform basis arrangements adopted by previous scalable Neural Radiance Field (NeRF) representations. We also suggest scene-adaptive virtual viewpoints to compensate for geometric deficiencies inherent in view configurations in the input trajectory and impose the necessary regularization. We present a comprehensive analysis and discussion regarding rendering quality and memory requirements in several large-scale indoor scenes, demonstrating significant enhancements compared to baselines that employ regular placements.