TensoRF: Tensorial Radiance Fields
This addresses the computational and memory bottlenecks in neural radiance field reconstruction for 3D scene rendering, representing a strong incremental improvement over existing methods.
The paper tackles the problem of modeling and reconstructing radiance fields by introducing TensoRF, which represents scenes as a 4D tensor factorized into compact components, achieving faster reconstruction (<30 min for CP, <10 min for VM) with better rendering quality and smaller model sizes (<4 MB for CP, <75 MB for VM) compared to NeRF and previous state-of-the-art methods.
We present TensoRF, a novel approach to model and reconstruct radiance fields. Unlike NeRF that purely uses MLPs, we model the radiance field of a scene as a 4D tensor, which represents a 3D voxel grid with per-voxel multi-channel features. Our central idea is to factorize the 4D scene tensor into multiple compact low-rank tensor components. We demonstrate that applying traditional CP decomposition -- that factorizes tensors into rank-one components with compact vectors -- in our framework leads to improvements over vanilla NeRF. To further boost performance, we introduce a novel vector-matrix (VM) decomposition that relaxes the low-rank constraints for two modes of a tensor and factorizes tensors into compact vector and matrix factors. Beyond superior rendering quality, our models with CP and VM decompositions lead to a significantly lower memory footprint in comparison to previous and concurrent works that directly optimize per-voxel features. Experimentally, we demonstrate that TensoRF with CP decomposition achieves fast reconstruction (<30 min) with better rendering quality and even a smaller model size (<4 MB) compared to NeRF. Moreover, TensoRF with VM decomposition further boosts rendering quality and outperforms previous state-of-the-art methods, while reducing the reconstruction time (<10 min) and retaining a compact model size (<75 MB).