VoronoiNet : General Functional Approximators with Local Support

Williams, Francis; Parent-Lévesque, Jérôme; Nowrouzezahrai, Derek; Panozzo, Daniele; Yi, Kwang Moo; Tagliasacchi, Andrea

doi:10.1109/cvprw50498.2020.00140

Cited by 19 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beyond methods based on implicit surfaces, other shape reconstruction techniques exist which leverage different output representations. These representations include dense point clouds [51,40,73,49,50,72,56,69,70,17,36], polygonal meshes [30,6,19,29,24,62,12,38,27,53], manifold atlases [63,15,26,18,3], and voxel grids [10,60,28,67,61,23]. While our method focuses on shape reconstruction from points, past work has used neural fields to perform a variety of 3D tasks such as shape compression [57,64], shape prediction from images [41,37], voxel grid upsampling [48,41], reconstruction from rotated inputs [14] and articulated poses [13,71], and video to 3D [68,39].…”

Section: Related Workmentioning

confidence: 99%

Neural Fields as Learnable Kernels for 3D Reconstruction

Williams¹,

Gojčič²,

Khamis³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Neural Fields as Learnable Kernels for 3D Reconstruction

Williams¹,

Gojčič²,

Khamis³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compositions of more explicitly defined mesh primitives were introduced in [23]. [46,29] who split the 3D domain into Voronoi primitives and express their occupancies to delineate the surface.…”

Section: Shape Representationsmentioning

confidence: 99%

Augmenting Implicit Neural Shape Representations with Explicit Deformation Fields

Atzmon,

Novotny,

Vedaldi

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Firstly, we could select an appropriate number of stages to best represent the whole scene by using techniques from neural architecture search [40]. Secondly, learnable clustering [41] points could be exploited to make the branched networks more adaptive to complexity of parts of the underlying scene.…”

Section: Limitations and Future Workmentioning

confidence: 99%

Recursive-NeRF: An Efficient and Dynamically Growing NeRF

Yang¹,

Zhou²,

Peng³

et al. 2021

Preprint

View full text Add to dashboard Cite

View synthesis methods using implicit continuous shape representations learned from a set of images, such as the Neural Radiance Field (NeRF) method, have gained increasing attention due to their high quality imagery and scalability to high resolution. However, the heavy computation required by its volumetric approach prevents NeRF from being useful in practice; minutes are taken to render a single image of a few megapixels. Now, an image of a scene can be rendered in a level-of-detail manner, so we posit that a complicated region of the scene should be represented by a large neural network while a small neural network is capable of encoding a simple region, enabling a balance between efficiency and quality. Recursive-NeRF is our embodiment of this idea, providing an efficient and adaptive rendering and training approach for NeRF. The core of Recursive-NeRF learns uncertainties for query coordinates, representing the quality of the predicted color and volumetric intensity at each level. Only query coordinates with high uncertainties are forwarded to the next level to a bigger neural network with a more powerful representational capability. The final rendered image is a composition of results from neural networks of all levels. Our evaluation on three public datasets shows that Recursive-NeRF is more efficient than NeRF while providing state-of-the-art quality. The code will be available at https://github.com/Gword/Recursive-NeRF.

show abstract

VoronoiNet : General Functional Approximators with Local Support

Cited by 19 publications

References 14 publications

Neural Fields as Learnable Kernels for 3D Reconstruction

Neural Fields as Learnable Kernels for 3D Reconstruction

Augmenting Implicit Neural Shape Representations with Explicit Deformation Fields

Recursive-NeRF: An Efficient and Dynamically Growing NeRF

Contact Info

Product

Resources

About