Semantic View Synthesis

Huang, Hsin-Ping; Tseng, Hung-Yu; Lee, Hsin-Ying; Huang, Jia-Bin

doi:10.1007/978-3-030-58610-2_35

Cited by 31 publications

(17 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It shows that users preferred our results more than the baseline. e) Evaluating on other baselines: To show the generalization of our approach, we also applied the same procedure on pix2pixHD [12] and recently presented ASAPNet [51]. The results are in Table I.…”

Section: Methodsmentioning

confidence: 99%

A Shared Representation for Photorealistic Driving Simulators

Saadatnejad¹,

Liu²,

Mordan³

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs), providing high-fidelity images. The main challenge is synthesizing photorealistic images while following given constraints. In this work, we propose to improve the quality of generated images by rethinking the discriminator architecture. The focus is on the class of problems where images are generated given semantic inputs, such as scene segmentation maps or human body poses. We build on successful cGAN models to propose a new semanticallyaware discriminator that better guides the generator. We aim to learn a shared latent representation that encodes enough information to jointly do semantic segmentation, content reconstruction, along with a coarse-to-fine grained adversarial reasoning. The achieved improvements are generic and simple enough to be applied to any architecture of conditional image synthesis. We demonstrate the strength of our method on the scene, building, and human synthesis tasks across three different datasets. The code is available https://github.com/vita-epfl/SemDisc.

show abstract

Section: Methodsmentioning

confidence: 99%

A Shared Representation for Photorealistic Driving Simulators

Saadatnejad¹,

Liu²,

Mordan³

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…The data distribution is either modeled explicitly (e.g., variational autoencoder [17]) or implicitly (e.g., generative adversarial networks [5]). On the basis of unconditional generative models, conditional generative models target synthesizing images according to additional context such as image [4,19,25,33,45], segmentation mask [11,26,37,47], and text. The text conditions are often expressed in two formats: natural language sentences [40,42] or scene graphs [14].…”

Section: Related Workmentioning

confidence: 99%

RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval

Tseng

Lee

Jiang

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

“…Existing single-image view synthesis methods model the scene with point cloud [41,58], multi-plane image [56,22], or layered depth image [48,27]. Our method focuses on headshot portraits and uses an implicit function as the neural representation.…”

Section: Related Workmentioning

confidence: 99%

Portrait Neural Radiance Fields from a Single Image

Gao,

Shih,

Lai

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

https://portrait-nerf.github.io (a) Input (b) Novel view synthesis (c) FOV manipulation Figure 1. Applications of the proposed method. Given a single portrait image (a) as input, our method produces a portrait neural radiance field that facilitates photorealistic face editing tasks such as (b) novel view synthesis and (c) field-of-view (FOV) manipulation, where the left and right are rendered with wider and narrower camera FOVs, respectively.

show abstract

Semantic View Synthesis

Cited by 31 publications

References 51 publications

A Shared Representation for Photorealistic Driving Simulators

A Shared Representation for Photorealistic Driving Simulators

RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval

Portrait Neural Radiance Fields from a Single Image

Contact Info

Product

Resources

About