AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations

Giebenhain, Simon; Goldluecke, Bastian

doi:10.1109/3dv53792.2021.00113

Cited by 14 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MeshUDF [85] further extends DeepSDF to reconstruct open surfaces, which predicts unsigned distances of any given space point and generates the surface using their customized marching cubes. More recently, a few methods [86], [87] adopt networks based on transformer [88], [89] to help reconstruction. Note also that learning semantic priors enables reconstruction of surfaces from raw observations that are originally of no or less 3D shape information (e.g., as few as a single RGB image [5], [90], [91]), by training encoders that learn latent shape spaces from such observations.…”

Section: Learning Semantic Priorsmentioning

confidence: 99%

Surface Reconstruction from Point Clouds: A Survey and a Benchmark

Huang¹,

Wen²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Reconstruction of a continuous surface of two-dimensional manifold from its raw, discrete point cloud observation is a long-standing problem in computer vision and graphics research. The problem is technically ill-posed, and becomes more difficult considering that various sensing imperfections would appear in the point clouds obtained by practical depth scanning. In literature, a rich set of methods has been proposed, and reviews of existing methods are also provided. However, existing reviews are short of thorough investigations on a common benchmark. The present paper aims to review and benchmark existing methods in the new era of deep learning surface reconstruction. To this end, we contribute a large-scale benchmarking dataset consisting of both synthetic and real-scanned data; the benchmark includes object-and scene-level surfaces and takes into account various sensing imperfections that are commonly encountered in practical depth scanning. We conduct thorough empirical studies by comparing existing methods on the constructed benchmark, and pay special attention on robustness of existing methods against various scanning imperfections; we also study how different methods generalize in terms of reconstructing complex surface shapes. Our studies help identify the best conditions under which different methods work, and suggest some empirical findings. For example, while deep learning methods are increasingly popular in the research community, our systematic studies suggest that, surprisingly, a few classical methods perform even better in terms of both robustness and generalization; our studies also suggest that the practical challenges of misalignment of point sets from multi-view scanning, missing of surface points, and point outliers remain unsolved by all the existing surface reconstruction methods. We expect that the benchmark and our studies would be valuable both for practitioners and as a guidance for new innovations in future research. We make the benchmark publicly accessible at https://Gorilla-Lab-SCUT.github.io/SurfaceReconstructionBenchmark.

show abstract

Section: Learning Semantic Priorsmentioning

confidence: 99%

Surface Reconstruction from Point Clouds: A Survey and a Benchmark

Huang¹,

Wen²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The aforementioned methods can approximate the global implicit functions with [83,21,23,40,7,94] or without blending local implicit functions [37,8,18]. Our method shares the idea of approximating global implicit functions by blending local ones, but our novelty lies in that we allow the neural network to adaptively split shapes so that we can blend parts with spatial surface properties or intrinsic attributes in the latent space well.…”

Section: Related Workmentioning

confidence: 99%

Latent Partition Implicit with Surface Codes for 3D Representation

Chen¹,

Liu²,

Han³

2022

Preprint

View full text Add to dashboard Cite

Deep implicit functions have shown remarkable shape modeling ability in various 3D computer vision tasks. One drawback is that it is hard for them to represent a 3D shape as multiple parts. Current solutions learn various primitives and blend the primitives directly in the spatial space, which still struggle to approximate the 3D shape accurately.To resolve this problem, we introduce a novel implicit representation to represent a single 3D shape as a set of parts in the latent space, towards both highly accurate and plausibly interpretable shape modeling. Our insight here is that both the part learning and the part blending can be conducted much easier in the latent space than in the spatial space. We name our method Latent Partition Implicit (LPI), because of its ability of casting the global shape modeling into multiple local part modeling, which partitions the global shape unity. LPI represents a shape as Signed Distance Functions (SDFs) using surface codes. Each surface code is a latent code representing a part whose center is on the surface, which enables us to flexibly employ intrinsic attributes of shapes or additional surface properties. Eventually, LPI can reconstruct both the shape and the parts on the shape, both of which are plausible meshes. LPI is a multilevel representation, which can partition a shape into different numbers of parts after training. LPI can be learned without ground truth signed distances, point normals or any supervision for part partition. LPI outperforms the latest methods under the widely used benchmarks in terms of reconstruction accuracy and modeling interpretability. Our code, data and models are available at https://github.com/chenchao15/LPI.

show abstract