Vehicle Reconstruction and Texture Estimation Using Deep Implicit Semantic Template Mapping

We introduce VERTEX, an effective solution to recover 3D shape and intrinsic texture of vehicles from uncalibrated monocular input in real-world street environments. To fully utilize the template prior of vehicles, we propose a novel geometry and texture joint representation, based on implicit semantic template mapping. Compared to existing representations which infer 3D texture distribution, our method explicitly constrains the texture distribution on the 2D surface of the template as well as avoids limitations of fixed resolution and topology. Moreover, by fusing the global and local features together, our approach is capable to generate consistent and detailed texture in both visible and invisible areas. We also contribute a new synthetic dataset containing 830 elaborate textured car models labeled with sparse key points and rendered using Physically Based Rendering (PBRT) system with measured HDRI skymaps to obtain highly realistic images. Experiments demonstrate the superior performance of our approach on both testing dataset and in-the-wild images. Furthermore, the presented technique enables additional applications such as 3D vehicle texture transfer and material identification.

NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image

We propose NormalGAN, a fast adversarial learning-based method to reconstruct the complete and detailed 3D human from a single RGB-D image. Given a single front-view RGB-D image, NormalGAN performs two steps: front-view RGB-D rectification and back-view RGBD inference. The final model was then generated by simply combining the front-view and back-view RGB-D information. However, inferring backview RGB-D image with high-quality geometric details and plausible texture is not trivial. Our key observation is: Normal maps generally encode much more information of 3D surface details than RGB and depth images. Therefore, learning geometric details from normal maps is superior than other representations. In NormalGAN, an adversarial learning framework conditioned by normal maps is introduced, which is used to not only improve the front-view depth denoising performance, but also infer the back-view depth image with surprisingly geometric details. Moreover, for texture recovery, we remove shading information from the front-view RGB image based on the refined normal map, which further improves the quality of the back-view color inference. Results and experiments on both testing data set and real captured data demonstrate the superior performance of our approach. Given a consumer RGB-D sensor, NormalGAN can generate the complete and detailed 3D human reconstruction results in 20 fps, which further enables convenient interactive experiences in telepresence, AR/VR and gaming scenarios.

Power Allocation in Compressed Sensing of Non-uniformly Sparse Signals

This paper studies the problem of power allocation in compressed sensing when different components in the unknown sparse signal have different probability to be non-zero. Given the prior information of the non-uniform sparsity and the total power budget, we are interested in how to optimally allocate the power across the columns of a Gaussian random measurement matrix so that the mean squared reconstruction error is minimized. Based on the state evolution technique originated from the work by Donoho, Maleki, and Montanari, we revise the so called approximate message passing (AMP) algorithm for the reconstruction and quantify the MSE performance in the asymptotic regime. Then the closed form of the optimal power allocation is obtained. The results show that in the presence of measurement noise, uniform power allocation, which results in the commonly used Gaussian random matrix with i.i.d. entries, is not optimal for non-uniformly sparse signals. Empirical results are presented to demonstrate the performance gain.