A Super-Resolution Framework for High-Accuracy Multiview Reconstruction

DTexFusion: Dynamic Texture Fusion Using a Consumer RGBD Sensor

In addition to 3D geometry, accurate representation of texture is important when digitizing real objects in virtual worlds. Based on a single consumer RGBD sensor, accurate texture representation for static objects can be realized by fusing multi-frame information; however, extending the process to dynamic objects, which typically have time-varying textures, is difficult. Thus, to address this problem, we propose a compact keyframe-based representation that decouples a dynamic texture into a basic static texture and a set of multiplicative changing maps. With this representation, the proposed method first aligns textures recorded from multiple keyframes with the reconstructed dynamic geometry of the object. Errors in the alignment and geometry are then compensated in an innovative iterative linear optimization framework. With the reconstructed texture, we then employ a scheme to synthesize the dynamic object from arbitrary viewpoints. By considering temporal and local pose similarities jointly, dynamic textures in all keyframes are fused to guarantee high-quality image generation. Experimental results demonstrate that the proposed method handles various dynamic objects, including faces, bodies, cloth, and toys. In addition, qualitative and quantitative comparisons demonstrate that the proposed method outperforms state-of-the-art solutions.

Photometric Depth Super-Resolution

This study explores the use of photometric techniques (shape-from-shading and uncalibrated photometric stereo) for upsampling the low-resolution depth map from an RGB-D sensor to the higher resolution of the companion RGB image. A single-shot variational approach is first put forward, which is effective as long as the target's reflectance is piecewise-constant. It is then shown that this dependency upon a specific reflectance model can be relaxed by focusing on a specific class of objects (e.g., faces), and delegate reflectance estimation to a deep neural network. A multi-shot strategy based on randomly varying lighting conditions is eventually discussed. It requires no training or prior on the reflectance, yet this comes at the price of a dedicated acquisition setup. Both quantitative and qualitative evaluations illustrate the effectiveness of the proposed methods on synthetic and real-world scenarios.

A Review of Techniques for 3D Reconstruction of Indoor Environments

Indoor environment model reconstruction has emerged as a significant and challenging task in terms of the provision of a semantically rich and geometrically accurate indoor model. Recently, there has been an increasing amount of research related to indoor environment reconstruction. Therefore, this paper reviews the state-of-the-art techniques for the three-dimensional (3D) reconstruction of indoor environments. First, some of the available benchmark datasets for 3D reconstruction of indoor environments are described and discussed. Then, data collection of 3D indoor spaces is briefly summarized. Furthermore, an overview of the geometric, semantic, and topological reconstruction of the indoor environment is presented, where the existing methodologies, advantages, and disadvantages of these three reconstruction types are analyzed and summarized. Finally, future research directions, including technique challenges and trends, are discussed for the purpose of promoting future research interest. It can be concluded that most of the existing indoor environment reconstruction methods are based on the strong Manhattan assumption, which may not be true in a real indoor environment, hence limiting the effectiveness and robustness of existing indoor environment reconstruction methods. Moreover, based on the hierarchical pyramid structures and the learnable parameters of deep-learning architectures, multi-task collaborative schemes to share parameters and to jointly optimize each other using redundant and complementary information from different perspectives show their potential for the 3D reconstruction of indoor environments. Furthermore, indoor–outdoor space seamless integration to achieve a full representation of both interior and exterior buildings is also heavily in demand.

Surface Motion Capture Animation Synthesis

We propose to generate novel animations from a set of elementary examples of video-based surface motion capture, under user-specified constraints. 4D surface capture animation is motivated by the increasing demand from media production for highly realistic 3D content. To this aim, data driven strategies that consider video-based information can produce animation with real shapes, kinematics and appearances. Our animations rely on the combination and the interpolation of textured 3D mesh data, which requires examining two aspects: (1) Shape geometry and (2) appearance. First, we propose an animation synthesis structure for the shape geometry, the Essential graph, that outperforms standard Motion graphs in optimality with respect to quantitative criteria, and we extend optimized interpolated transition algorithms to mesh data. Second, we propose a compact view-independent representation for the shape appearance. This representation encodes subject appearance changes due to viewpoint and illumination, and due to inaccuracies in geometric modelling independently. Besides providing compact representations, such decompositions allow for additional applications such as interpolation for animation.