paper-with-me

홈 › Papers

Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement

2020-03-27 · ICCV 2019 10 · Sai Bi, Kalyan Sunkavalli, Federico Perazzi, Eli Shechtman, Vladimir Kim, Ravi Ramamoorthi

We present a method to improve the visual realism of low-quality, synthetic images, e.g. OpenGL renderings. Training an unpaired synthetic-to-real translation network in image space is severely under-constrained and produces visible artifacts. Instead, we propose a semi-supervised approach that operates on the disentangled shading and albedo layers of the image. Our two-stage pipeline first learns to predict accurate shading in a supervised fashion using physically-based renderings as targets, and further increases the realism of the textures and shading with an improved CycleGAN network. Extensive evaluations on the SUNCG indoor scene dataset demonstrate that our approach yields more realistic images compared to other state-of-the-art approaches. Furthermore, networks trained on our generated "real" images predict more accurate depth and normals than domain adaptation approaches, suggesting that improving the visual realism of the images can be more effective than imposing task-specific losses.

📄 PDF Abstract BibTeX arXiv:2003.12649

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementDomain AdaptationSynthetic-to-Real TranslationTranslation

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
Residual Connection 설명 없음
PatchGAN 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Tanh Activation 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Instance Normalization Instance Normalization (also known as contrast normalization) is a normalization layer where: $$ y_{tijk} = \frac{x_{tijk} - \mu_{ti}}{\sqrt{\sigma_{ti}^2 +…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation

2021-03-25 · CVPR 2021 1 · Yuntong Ye, Yi Chang, Hanyu Zhou, Luxin Yan

Existing deep learning-based image deraining methods have achieved promising performance for synthetic rainy images, typically rely on the pairs of sharp images and simulated rainy counterparts. However, these methods su…

DisentanglementRain RemovalTranslation

Identity From Here, Pose From There: Self-Supervised Disentanglement and Generation of Objects Using Unlabeled Videos

2019-10-01 · ICCV 2019 10 · Fanyi Xiao, Haotian Liu, Yong Jae Lee

We propose a novel approach that disentangles the identity and pose of objects for image generation. Our model takes as input an ID image and a pose image, and generates an output image with the identity of the ID image …

DisentanglementDiversityImage Generation

Content Disentanglement for Semantically Consistent Synthetic-to-Real Domain Adaptation

2021-05-18 · Mert Keser, Artem Savkin, Federico Tombari

Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving. However, deep learning perception algorithms trained solely on synthetic data encounter serious performance dr…

Autonomous DrivingDisentanglementDomain AdaptationSemantic Segmentation+1

Unsupervised Disentanglement Learning by intervention

2021-01-01 · Weishen Pan, Sen Cui, ChangShui Zhang

Recently there has been an increased interest in unsupervised learning of disentangled representations on the data generated from variation factors. Existing works rely on the assumption that the generative factors are i…

DisentanglementTranslation

Semi-Supervised StyleGAN for Disentanglement Learning

2020-03-06 · ICML 2020 1 · Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debnath 외

Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, prima…

DisentanglementRepresentation Learning