Meshlet Priors for 3D Mesh Reconstruction

Badki, Abhishek; Gallo, Orazio; Kautz, Jan; Sen, Pradeep

doi:10.1109/cvpr42600.2020.00292

Cited by 52 publications

(32 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some works (Groueix et al, 2018;Pan et al, 2018;Wang et al, 2020) use a template mesh that is deformed to match the shape of the object to be reconstructed or one of its parts, whereas Chen et al ( 2020) combine a fixed number of planes whose parameters are inferred using a NN to first produce some convexes, that are then combined to produce the final concave shape. Badki et at. (2020) use meshlets, or mesh patches, and iteratively deform and transform them to match the target shape by optimizing a given loss function; since meshlets are fitted locally, this method is more robust to unseen objects and poses during training compared to approaches that favor global features.…”

Section: Deep Learning-based 3d Object Reconstruction Methodsmentioning

confidence: 99%

3d Scene Reconstruction System Based on a Mobile Device

2021

IJCISIS

View full text Add to dashboard Cite

Section: Deep Learning-based 3d Object Reconstruction Methodsmentioning

confidence: 99%

3d Scene Reconstruction System Based on a Mobile Device

2021

IJCISIS

View full text Add to dashboard Cite

“…It has become possible recently to regress implicit functions in the form of binary occupancy or signed distances [63,8,38,41]. Similarly, other forms of learned 3D priors have been applied to convert or refine existing shape representations [59,4,13].…”

Section: Related Workmentioning

confidence: 99%

SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators

Luo¹,

Li²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent advances in deep generative models have led to immense progress in 3D shape synthesis. While existing models are able to synthesize shapes represented as voxels, point-clouds, or implicit functions, these methods only indirectly enforce the plausibility of the final 3D shape surface.Here we present a 3D shape synthesis framework (SurfGen) that directly applies adversarial training to the object surface. Our approach uses a differentiable spherical projection layer to capture and represent the explicit zero isosurface of an implicit 3D generator as functions defined on the unit sphere. By processing the spherical representation of 3D object surfaces with a spherical CNN in an adversarial setting, our generator can better learn the statistics of natural shape surfaces. We evaluate our model on largescale shape datasets, and demonstrate that the end-to-end trained model is capable of generating high fidelity 3D shapes with diverse topology. Code is available at https: //github.com/aluo-x/NeuralRaycaster.

show abstract

“…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%