Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency
This work addresses the challenge of efficient and accurate 3D scene reconstruction from limited views for applications like VR/AR, though it is incremental in improving existing few-shot radiance field methods.
The paper tackles the problem of unreliable pseudo novel view synthesis in few-shot radiance fields by proposing ReVoRF, a voxel-based optimization framework that uses relative geometric consistency and reliability-guided learning. The result is a 5% improvement in PSNR over existing methods, with rendering at 3 FPS and training in 7 minutes for a 360° scene.
We propose a voxel-based optimization framework, ReVoRF, for few-shot radiance fields that strategically address the unreliability in pseudo novel view synthesis. Our method pivots on the insight that relative depth relationships within neighboring regions are more reliable than the absolute color values in disoccluded areas. Consequently, we devise a bilateral geometric consistency loss that carefully navigates the trade-off between color fidelity and geometric accuracy in the context of depth consistency for uncertain regions. Moreover, we present a reliability-guided learning strategy to discern and utilize the variable quality across synthesized views, complemented by a reliability-aware voxel smoothing algorithm that smoothens the transition between reliable and unreliable data patches. Our approach allows for a more nuanced use of all available data, promoting enhanced learning from regions previously considered unsuitable for high-quality reconstruction. Extensive experiments across diverse datasets reveal that our approach attains significant gains in efficiency and accuracy, delivering rendering speeds of 3 FPS, 7 mins to train a $360^\circ$ scene, and a 5\% improvement in PSNR over existing few-shot methods. Code is available at https://github.com/HKCLynn/ReVoRF.