NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors

Wang, Jiepeng; Wang, Peng; Long, Xiaoxiao; Theobalt, Christian; Komura, Taku; Liu, Lingjie; Wang, Wenping

doi:10.1007/978-3-031-19824-3_9

Cited by 116 publications

(172 citation statements)

References 35 publications

Supporting

Mentioning

172

Contrasting

Order By: Relevance

“…Many variants of NeRF-like models have since appeared. For instance, some [24,48,50] use sign distance functions (SDFs) to recover cleaner geometry. These approaches assume that dozens if not hundreds of views of each scene are available for reconstruction.…”

Section: Related Workmentioning

confidence: 99%

RealFusion: 360° Reconstruction of Any Object from a Single Image

Melas-Kyriazi¹,

Rupprecht²,

Laina³

et al. 2023

Preprint

View full text Add to dashboard Cite

https://lukemelas.github.io/realfusion Figure 1. RealFusion generates a full 360 • reconstruction of any object given a single image of it (left column). It does so by leveraging an existing diffusion-based 2D image generator. From the given image, it synthesizes a prompt that causes the diffusion model to "dream up" other views of the object. It then extracts a neural radiance field from the original image and the diffusion model-based prior, thereby reconstructing the object in full. Both appearance and geometry are reconstructed faithfully and extrapolated in a plausible manner (see the textured and shaded reconstructions from different viewpoints).

show abstract

Section: Related Workmentioning

confidence: 99%

RealFusion: 360° Reconstruction of Any Object from a Single Image

Melas-Kyriazi¹,

Rupprecht²,

Laina³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Neural Fields are neural networks that maps spatial coordinate to a signal. Recent research has shown that neural fields are effective in representing a wide variety of signals such as images [60,62], 3D shapes [3,17,41,50,71], 3D scenes [20,27,31,51,59] and radiance fields [4,5,6,23,32,35,37,38,40,43,44,45,47,48,52,54,59,61,67,72,73,74,76]. However, neural fields typically operate as black boxes, which hinders the application of neural fields to some signal decomposition and manipulation tasks as discussed in Sec.…”

Section: Related Workmentioning

confidence: 99%

Polynomial Neural Fields for Subband Decomposition and Manipulation

Yang¹,

Benaim²,

Jampani³

et al. 2023

Preprint

View full text Add to dashboard Cite

Neural fields have emerged as a new paradigm for representing signals, thanks to their ability to do it compactly while being easy to optimize. In most applications, however, neural fields are treated like black boxes, which precludes many signal manipulation tasks. In this paper, we propose a new class of neural fields called polynomial neural fields (PNFs). The key advantage of a PNF is that it can represent a signal as a composition of a number of manipulable and interpretable components without losing the merits of neural fields representation. We develop a general theoretical framework to analyze and design PNFs. We use this framework to design Fourier PNFs, which match state-of-the-art performance in signal representation tasks that use neural fields. In addition, we empirically demonstrate that Fourier PNFs enable signal manipulation applications such as texture transfer and scale-space interpolation. Code is available at https://github.com/stevenygd/PNF. * Equal contribution. Part of this work was done while Guandao was a student researcher at Google. 36th Conference on Neural Information Processing Systems (NeurIPS 2022).

show abstract

“…NeRF is optimized from images with volume rendering techniques, which produces impressive image synthesis results. Many works improve NeRF in various aspects, including rendering quality [3,4], rendering speed [22,27,39,63,98], scene scale [64,81,88,93], and reconstruction quality [50,89,95]. Some methods [18,37,52,59] extend NeRF to dynamic scenes.…”

Section: Related Workmentioning

confidence: 99%