English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we present InSeGAN, an unsupervised 3D generative adversarialnetwork (GAN) for segmenting (nearly) identical instances of rigid objects indepth images. Using an analysis-by-synthesis approach, we design a novel GANarchitecture to synthesize a multiple-instance depth image with independentcontrol over each instance. InSeGAN takes in a set of code vectors (e.g.,random noise vectors), each encoding the 3D pose of an object that isrepresented by a learned implicit object template. The generator has twodistinct modules. The first module, the instance feature generator, uses eachencoded pose to transform the implicit template into a feature maprepresentation of each object instance. The second module, the depth imagerenderer, aggregates all of the single-instance feature maps output by thefirst module and generates a multiple-instance depth image. A discriminatordistinguishes the generated multiple-instance depth images from thedistribution of true depth images. To use our model for instance segmentation,we propose an instance pose encoder that learns to take in a generated depthimage and reproduce the pose code vectors for all of the object instances. Toevaluate our approach, we introduce a new synthetic dataset, "Insta-10",consisting of 100,000 depth images, each with 5 instances of an object from oneof 10 classes. Our experiments on Insta-10, as well as on real-world noisydepth images, show that InSeGAN achieves state-of-the-art performance, oftenoutperforming prior methods by large margins.

InSeGAN: A Generative Approach to Segmenting Identical Instances in Depth Images