Implicit Shape Completion via Adversarial Shape Priors
원문 초록
We present a novel neural implicit shape method for partial point cloud completion. To that end, we combine a conditional Deep-SDF architecture with learned, adversarial shape priors. More specifically, our network converts partial inputs into a global latent code and then recovers the full geometry via an implicit, signed distance generator. Additionally, we train a PointNet++ discriminator that impels the generator to produce plausible, globally consistent reconstructions. In that way, we effectively decouple the challenges of predicting shapes that are both realistic, i.e. imitate the training set's pose distribution, and accurate in the sense that they replicate the partial input observations. In our experiments, we demonstrate state-of-the-art performance for completing partial shapes, considering both man-made objects (e.g. airplanes, chairs, ...) and deformable shape categories (human bodies). Finally, we show that our adversarial training approach leads to visually plausible reconstructions that are highly consistent in recovering missing parts of a given object.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding
SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance
Parametric Point Cloud Completion for Polygonal Surface Reconstruction
DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows
PointSea: Point Cloud Completion via Self-structure Augmentation
DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion
토론
이 논문과 연결된 포럼 글이 아직 없습니다.