Yiheng Zhang — Page 3

arXiv2018

Light Transport Simulation via Generalized Multiple Importance Sampling

Multiple importance sampling (MIS) is employed to reduce variance of estimators, but when sampling and weighting are not suitable to the integrand, the estimators would have extra variance. Therefore, robust light transport simulation algorithms based on Monte Carlo sampling for different types of scenes are still uncompleted. In this paper, we address this problem by present a general method, named generalized multiple importance sampling (GMIS), to enhance the robustness of light transport simulation based on MIS. GMIS combines different sampling techniques and weighting functions, extending MIS to a more generalized framework. Meanwhile, we implement the GMIS in common renderers and illustrate how it increase the robustness of light transport simulation. Experiments show that, by applying GMIS, we obtain better convergence performance and lower variance, and increase the rendering of ambient light and specular shadow effects apparently.

cs.GR↗

arXiv2018

Fully Convolutional Adaptation Networks for Semantic Segmentation

The recent advances in deep neural networks have convincingly demonstrated high capability in learning vision models on large datasets. Nevertheless, collecting expert labeled datasets especially with pixel-level annotations is an extremely expensive process. An appealing alternative is to render synthetic data (e.g., computer games) and generate ground truth automatically. However, simply applying the models learnt on synthetic images may lead to high generalization error on real images due to domain shift. In this paper, we facilitate this issue from the perspectives of both visual appearance-level and representation-level domain adaptation. The former adapts source-domain images to appear as if drawn from the "style" in the target domain and the latter attempts to learn domain-invariant representations. Specifically, we present Fully Convolutional Adaptation Networks (FCAN), a novel deep architecture for semantic segmentation which combines Appearance Adaptation Networks (AAN) and Representation Adaptation Networks (RAN). AAN learns a transformation from one domain to the other in the pixel space and RAN is optimized in an adversarial learning manner to maximally fool the domain discriminator with the learnt source and target representations. Extensive experiments are conducted on the transfer from GTA5 (game videos) to Cityscapes (urban street scenes) on semantic segmentation and our proposal achieves superior results when comparing to state-of-the-art unsupervised adaptation techniques. More remarkably, we obtain a new record: mIoU of 47.5% on BDDS (drive-cam videos) in an unsupervised setting.

cs.CV↗