CVGROct 2, 2022

IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis

arXiv:2210.00647v361 citationsh-index: 123
Originality Incremental advance
AI Analysis

This enables real-time augmented applications like recoloring and illumination variation for room-scale scenes, representing an incremental advance over object-specific methods.

The authors tackled the problem of editable novel view synthesis for room-scale scenes by introducing intrinsic decomposition into NeRF-based neural rendering, achieving multi-view consistent intrinsic decomposition results and high-fidelity synthesis.

Existing inverse rendering combined with neural rendering methods can only perform editable novel view synthesis on object-specific scenes, while we present intrinsic neural radiance fields, dubbed IntrinsicNeRF, which introduce intrinsic decomposition into the NeRF-based neural rendering method and can extend its application to room-scale scenes. Since intrinsic decomposition is a fundamentally under-constrained inverse problem, we propose a novel distance-aware point sampling and adaptive reflectance iterative clustering optimization method, which enables IntrinsicNeRF with traditional intrinsic decomposition constraints to be trained in an unsupervised manner, resulting in multi-view consistent intrinsic decomposition results. To cope with the problem that different adjacent instances of similar reflectance in a scene are incorrectly clustered together, we further propose a hierarchical clustering method with coarse-to-fine optimization to obtain a fast hierarchical indexing representation. It supports compelling real-time augmented applications such as recoloring and illumination variation. Extensive experiments and editing samples on both object-specific/room-scale scenes and synthetic/real-word data demonstrate that we can obtain consistent intrinsic decomposition results and high-fidelity novel view synthesis even for challenging sequences.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes