Deep Meta Functionals for Shape Representation

Littwin, Gidi; Wolf, Lior

doi:10.1109/iccv.2019.00191

Cited by 64 publications

(52 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ravi et al [14] use the LSTM to learn an update rule for training a neural network by replacing the stochastic gradient descent optimizer in few-shot learning. In 3D computer vision, Littwin et al [10] achieve satisfying performance in the 3D shape representation task by mapping the input point cloud to the parameters of a deep neural network. In this paper, we first propose a meta-learning strategy which use a meta-part segmentation learner to learn the general information over a variety of part segmentation tasks so that it can estimate the parameters of the part segmentation learner and make the part segmentation learner's network rapidly adapt to new part segmentation tasks.…”

Section: Meta-learning Methodsmentioning

confidence: 99%

3D Meta-Segmentation Neural Network

Hao,

Fang

2021

Preprint

View full text Add to dashboard Cite

Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suffer from unsatisfied generalization abilities to unseen classes with limited data. To address this problem, we present a novel meta-learning strategy that regards the 3D shape segmentation function as a task. By training over a number of 3D part segmentation tasks, our method is capable to learn the prior over the respective 3D segmentation function space which leads to an optimal model that is rapidly adapting to new part segmentation tasks. To implement our meta-learning strategy, we propose two novel modules: meta part segmentation learner and part segmentation learner. During the training process, the part segmentation learner is trained to complete a specific part segmentation task in the few-shot scenario. In the meantime, the meta part segmentation learner is trained to capture the prior from multiple similar part segmentation tasks. Based on the learned information of task distribution, our meta part segmentation learner is able to dynamically update the part segmentation learner with optimal parameters which enable our part segmentation learner to rapidly adapt and have great generalization ability on new part segmentation tasks. We demonstrate that our model achieves superior part segmentation performance with the few-shot setting on the widely used dataset: ShapeNet.

show abstract

Section: Meta-learning Methodsmentioning

confidence: 99%

3D Meta-Segmentation Neural Network

Hao,

Fang

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Coordinates conditioning. Coordinates conditioning is the most popular among the NeRF-based [45,40] and occupancy-modeling [44,9,35] methods. [48,7,59] trained a coordinate-based generator that models a volume which is then rendered and passed to a discriminator.…”

Section: Related Workmentioning

confidence: 99%

Aligning Latent and Image Spaces to Connect the Unconnectable

Skorokhodov¹,

Sotnikov²,

Elhoseiny³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Hypernetwork is the auxiliary neural network that produces the weights for other network (often called as primary network). They were first proposed by Ha et al [14] and have been used in a wide range of applications from semantic segmentation [35], 3D scene representation [30,43], neural architecture search (NAS) [54] to continual learning [46]. In this study, we design the hypernetworks to improve the quality of our GAN inversion method.…”

Section: Related Workmentioning

confidence: 99%

HyperInverter: Improving StyleGAN Inversion via Hypernetwork

Dinh¹,

Tran²,

Nguyen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Real-world image manipulation has achieved fantastic progress in recent years as a result of the exploration and utilization of GAN latent spaces. GAN inversion is the first step in this pipeline, which aims to map the real image to the latent code faithfully. Unfortunately, the majority of existing GAN inversion methods fail to meet at least one of the three requirements listed below: high reconstruction quality, editability, and fast inference. We present a novel two-phase strategy in this research that fits all requirements at the same time. In the first phase, we train an encoder to map the input image to StyleGAN2 W-space, which was proven to have excellent editability but lower reconstruction quality. In the second phase, we supplement the reconstruction ability in the initial phase by leveraging a series of hypernetworks to recover the missing information during inversion. These two steps complement each other to yield high reconstruction quality thanks to the hypernetwork branch and excellent editability due to the inversion done in the W-space. Our method is entirely encoder-based, resulting in extremely fast inference. Extensive experiments on two challenging datasets demonstrate the superiority of our method. 1

show abstract

Deep Meta Functionals for Shape Representation

Cited by 64 publications

References 31 publications

3D Meta-Segmentation Neural Network

3D Meta-Segmentation Neural Network

Aligning Latent and Image Spaces to Connect the Unconnectable

HyperInverter: Improving StyleGAN Inversion via Hypernetwork

Contact Info

Product

Resources

About