Editing Conditional Radiance Fields

13 May 2021  ·  Steven Liu, Xiuming Zhang, Zhoutong Zhang, Richard Zhang, Jun-Yan Zhu, Bryan Russell ·

A neural radiance field (NeRF) is a scene model supporting high-quality view synthesis, optimized per scene. In this paper, we explore enabling user editing of a category-level NeRF - also known as a conditional radiance field - trained on a shape category... Specifically, we introduce a method for propagating coarse 2D user scribbles to the 3D space, to modify the color or shape of a local region. First, we propose a conditional radiance field that incorporates new modular network components, including a shape branch that is shared across object instances. Observing multiple instances of the same category, our model learns underlying part semantics without any supervision, thereby allowing the propagation of coarse 2D user scribbles to the entire 3D region (e.g., chair seat). Next, we propose a hybrid network update strategy that targets specific network components, which balances efficiency and accuracy. During user interaction, we formulate an optimization problem that both satisfies the user's constraints and preserves the original object structure. We demonstrate our approach on various editing tasks over three shape datasets and show that it outperforms prior neural editing approaches. Finally, we edit the appearance and shape of a real photograph and show that the edit propagates to extrapolated novel views. read more

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Novel View Synthesis Dosovitskiy Chairs Single NeRF + Share./Inst. Net PSNR 21.78 # 1
LPIPS 0.141 # 1
Novel View Synthesis PhotoShape Single NeRF + Share./Inst. Net PSNR 37.67 # 1
LPIPS 0.022 # 1