SIGGRAPH Asia 2022 Papers

Reverse Engineering a CAD shape from other representations is an important geometric processing step for many downstream applications. In this work, we introduce a novel neural network architecture to solve this challenging task and approximate a smoothed signed distance function with an editable, constrained, prismatic CAD model. During training, our method reconstructs the input geometry in the voxel space by decomposing the shape into a series of 2D profile images and 1D envelope functions. These can then be recombined in a differentiable way allowing a geometric loss function to be defined. During inference, we obtain the CAD data by first searching a database of 2D constrained sketches to find curves which approximate the profile images, then extrude them and use Boolean operations to build the final CAD model. Our method approximates the target shape more closely than other methods and outputs highly editable constrained parametric sketches which are compatible with existing CAD software.

We present a novel semantic model for human head defined with neural radiance field. The 3D-consistent head model consist of a set of disentangled and interpretable bases, and can be driven by low-dimensional expression coefficients. Thanks to the powerful representation ability of neural radiance field, the constructed model can represent complex facial attributes including hair, wearings, which can not be represented by traditional mesh blendshape. To construct the personalized semantic facial model, we propose to define the bases as several multi-level voxel fields. With a short monocular RGB video as input, our method can construct the subject's semantic facial NeRF model with only ten to twenty minutes, and can render a photorealistic human head image in tens of miliseconds with a given expression coefficient and view direction. With this novel representation, we apply it to many tasks like facial retargeting and expression editing. Experimental results demonstrate its strong representation ability and training/inference speed. Demo videos and released code are provided in our project page: https://ustc3dv.github.io/NeRFBlendShape/

This paper presents an approach that reconstructs a hand-held object from a monocular video. In contrast to many recent methods that directly predict object geometry by a trained network, the proposed approach does not require any learned prior about the object and is able to recover more accurate and detailed object geometry. The key idea is that the hand motion naturally provides multiple views of the object and the motion can be reliably estimated by a hand pose tracker. Then, the object geometry can be recovered by solving a multi-view reconstruction problem. We devise an implicit neural representation-based method to solve the reconstruction problem and address the issues of imprecise hand pose estimation, relative hand-object motion, and insufficient geometry optimization for small objects. We also provide a newly collected dataset with 3D ground truth to validate the proposed approach. The dataset and code will be released at https://dihuangdh.github.io/hhor.

In this study, we developed a flow to simulate anisotropy in multi-color printing of a FFF 3D printer. There are previous methods for simulating layered marks from gcode, which is a 3D printer control statement, and multi-color printing by switching filament colors and their simulators. However, there was no simulator for the case where color anisotropy exists in a single path, which is the target of this study. Since the coloring of this method is based on a completely different principle from existing methods, it is difficult to predict the results. Our simulator tool was very useful in rendering multi-color 3D printed models. Furthermore, a more sophisticated simulation of the placement of objects in real space was performed based on the highly realistic images created by physical-based rendering. The simulation also worked in VR space and showed an optimal preview at the architectural scale.

As virtual reality (VR) headsets continue to achieve ever more immersive visuals along the axes of resolution, field of view, focal cues, distortion mitigation, and so on, the luminance and dynamic range of these devices falls far short of widely available consumer televisions. While work remains to be done on the display architecture side, power and weight limitations in head-mounted displays pose a challenge for designs aiming for high luminance. In this paper, we seek to gain a basic understanding of VR user preferences for display luminance values in relation to known, real-world luminances for immersive, natural scenes. To do so, we analyze the luminance characteristics of an existing high-dynamic-range (HDR) panoramic image dataset, build an HDR VR headset capable of reproducing over 20,000 nits peak luminance, and conduct a first-of-its-kind study on user brightness preferences in VR. We conclude that current commercial VR headsets do not meet user preferences for display luminance, even for indoor scenes.

In light of the COVID-19 pandemic, wearing a mask is crucial to avoid contracting infectious diseases. However, wearing a mask is known to impair communication functions. This study aims to address the communication difficulties caused by wearing a mask and provide a strategy for aiding in understanding the speaker’s speech through facial animation. Facial animation is generated in real-time, and upper facial information is processed to detect the speaker’s emotions, generating a lower facial expression. In addition, the system detects the mask’s shape and enables accurate registration in the proper position. This technology can improve communication and alleviate challenges associated with communication between persons wearing face masks.

We present Recurrent Feature Alignment (ReFA), an end-to-end neural network for the very rapid creation of production-grade face assets from multi-view images. ReFA is on par with the industrial pipelines in quality for producing accurate, complete, registered, and textured assets directly applicable to physically-based rendering, but produces the asset end-to-end, fully automatically at a significantly faster speed at 4.5 FPS, which is unprecedented among neural-based techniques. Our method represents face geometry as a position map in the UV space. The network first extracts per-pixel features in both the multi-view image space and the UV space. A recurrent module then iteratively optimizes the geometry by projecting the image-space features to the UV space and comparing them with a reference UV-space feature. The optimized geometry then provides pixel-aligned signals for the inference of high-resolution textures. Experiments have validated that ReFA achieves a median error of 0.603mm in geometry reconstruction, is robust to extreme pose and expression, and excels in sparse-view settings. We believe that the progress achieved by our network enables lightweight, fast face assets acquisition that significantly boosts the downstream applications, such as avatar creation and facial performance capture. It will also enable massive database capturing for deep learning purposes.

Feature lines are important geometric cues in characterizing the structure of a CAD model. Despite great progress in both explicit reconstruction and implicit reconstruction, it remains a challenging task to reconstruct a polygonal surface equipped with feature lines, especially when the input point cloud is noisy and lacks faithful normal vectors. In this paper, we develop a multistage algorithm, named RFEPS, to address this challenge. The key steps include (1) denoising the point cloud based on the assumption of local planarity, (2) identifying the feature-line zone by optimization of discrete optimal transport, (3) augmenting the point set so that sufficiently many additional points are generated on potential geometry edges, and (4) generating a polygonal surface that interpolates the augmented point set based on restricted power diagram. We demonstrate through extensive experiments that RFEPS, benefiting from the edge-point augmentation and the feature preserving explicit reconstruction, outperforms state of the art methods in terms of the reconstruction quality, especially in terms of the ability to reconstruct missing feature lines.

Real-time tracking of human body motion is crucial for interactive and immersive experiences in AR/VR. However, very limited sensor data about the body is available from standalone wearable devices such as HMDs (Head Mounted Devices) or AR glasses. In this work, we present a reinforcement learning framework that takes in sparse signals from an HMD and two controllers, and simulates plausible and physically valid full body motions. Using high quality full body motion as dense supervision during training, a simple policy network can learn to output appropriate torques for the character to balance, walk, and jog, while closely following the input signals. Our results demonstrate surprisingly similar leg motions to ground truth without any observations of the lower body, even when the input is only the 6D transformations of the HMD. We also show that a single policy can be robust to diverse locomotion styles, different body sizes, and novel environments.

Streaming rendered 3D content over a network to a thin client device, such as a phone or a VR/AR headset, brings high-fidelity graphics to platforms where it would not normally possible due to thermal, power, or cost constraints. Streamed 3D content must be transmitted with a representation that is both robust to latency and potential network dropouts. Transmitting a video stream and reprojecting to correct for changing viewpoints fails in the presence of disocclusion events; streaming scene geometry and performing high-quality rendering on the client is not possible on limited-power mobile GPUs. To balance the competing goals of disocclusion robustness and minimal client workload, we introduce QuadStream, a new streaming content representation that reduces motion-to-photon latency by allowing clients to efficiently render novel views without artifacts caused by disocclusion events. Motivated by traditional macroblock approaches to video codec design, we decompose the scene seen from positions in a view cell into a series of quad proxies, or view-aligned quads from multiple views. By operating on a rasterized G-Buffer, our approach is independent of the representation used for the scene itself; the resulting QuadStream is an approximate geometric representation of the scene that can be reconstructed by a thin client to render both the current view and nearby adjacent views. Our technical contributions are an efficient parallel quad generation, merging, and packing strategy for proxy views covering potential client movement in a scene; a packing and encoding strategy that allows masked quads with depth information to be transmitted as a frame-coherent stream; and an efficient rendering approach for rendering our QuadStream representation into entirely novel views on thin clients. We show that our approach achieves superior quality compared both to video data streaming methods, and to geometry-based streaming.

Color vision tests are conducted based on subjective responses; however, since subjective responses can be biased and are not uniformly applicable to all individuals, an objective method is required. In this study, we developed a quantitative and user-friendly color vision test, which utilized a psychophysical method based on pupillary responses to color flicker stimuli sampled from the confusion line. The results revealed that power spectral density of pupillary oscillations increased corresponded to the color differences. Our system could eventually lead to a feasible color testing method.

Holographic displays promise to deliver unprecedented display capabilities in augmented reality applications, featuring a wide field of view, wide color gamut, spatial resolution, and depth cues all in a compact form factor. While emerging holographic display approaches have been successful in achieving large étendue and high image quality as seen by a camera, the large étendue also reveals a problem that makes existing displays impractical: the sampling of the holographic field by the eye pupil. Existing methods have not investigated this issue due to the lack of displays with large enough étendue, and, as such, they suffer from severe artifacts with varying eye pupil size and location. We show that the holographic field as sampled by the eye pupil is highly varying for existing display setups, and we propose pupil-aware holography that maximizes the perceptual image quality irrespective of the size, location, and orientation of the eye pupil in a near-eye holographic display. We validate the proposed approach both in simulations and on a prototype holographic display and show that our method eliminates severe artifacts and significantly outperforms existing approaches.

Figure 1: System overview. A remote worker captures the area with a camera and streams the image (we call it rst-person view) to our system. Then, the system estimates the camera’s position and direction from the image and the pre-scanned 3D geometry. Finally, our system generates a third-person view by overlapping the captured image and the location information on the geometry. The receiver can switch these views freely. (a) First-person view: The image captured by remote worker is displayed in the center, with the pre-scanned geometry around it. This view moves with the movement of the remote worker. (b) Switching between rst-person and third-person view: The receiver can switch between the two views. (c) Third-person view: The user can move the viewpoint freely in the geometry model. The rst-person view and the camera’s position are also displayed so that the receiver can know the location of the remote worker.

The trade-off between speed and fidelity in cloth simulation is a fundamental computational problem in computer graphics and computational design. Coarse cloth models provide the interactive performance required by designers, but they can not be simulated at higher resolutions ("up-resed") without introducing simulation artifacts and/or unpredicted outcomes, such as different folds, wrinkles and drapes. But how can a coarse simulation predict the result of an unconstrained, high-resolution simulation that has not yet been run? We propose Progressive Cloth Simulation (PCS), a new forward simulation method for efficient preview of cloth quasistatics on exceedingly coarse triangle meshes with consistent and progressive improvement over a hierarchy of increasingly higher-resolution models. PCS provides an efficient coarse previewing simulation method that predicts the coarse-scale folds and wrinkles that will be generated by a corresponding converged, high-fidelity C-IPC simulation of the cloth drape's equilibrium. For each preview PCS can generate an increasing-resolution sequence of consistent models that progress towards this converged solution. This successive improvement can then be interrupted at any point, for example, whenever design parameters are updated. PCS then ensures feasibility at all resolutions, so that predicted solutions remain intersection-free and capture the complex folding and buckling behaviors of frictionally contacting cloth.

Photorealistic digital re-aging of faces in video is becoming increasingly common in entertainment and advertising. But the predominant 2D painting workflow often requires frame-by-frame manual work that can take days to accomplish, even by skilled artists. Although research on facial image re-aging has attempted to automate and solve this problem, current techniques are of little practical use as they typically suffer from facial identity loss, poor resolution, and unstable results across subsequent video frames. In this paper, we present the first practical, fully-automatic and production-ready method for re-aging faces in video images. Our first key insight is in addressing the problem of collecting longitudinal training data for learning to re-age faces over extended periods of time, a task that is nearly impossible to accomplish for a large number of real people. We show how such a longitudinal dataset can be constructed by leveraging the current state-of-the-art in facial re-aging that, although failing on real images, does provide photoreal re-aging results on synthetic faces. Our second key insight is then to leverage such synthetic data and formulate facial re-aging as a practical image-to-image translation task that can be performed by training a well-understood U-Net architecture, without the need for more complex network designs. We demonstrate how the simple U-Net, surprisingly, allows us to advance the state of the art for re-aging real faces on video, with unprecedented temporal stability and preservation of facial identity across variable expressions, viewpoints, and lighting conditions. Finally, our new face re-aging network (FRAN) incorporates simple and intuitive mechanisms that provides artists with localized control and creative freedom to direct and fine-tune the re-aging effect, a feature that is largely important in real production pipelines and often overlooked in related research work.

We propose procedural modeling of crystal clusters. Based on crystallography, we model single crystals and then distribute single crystals on a base rock using a hierarchical sampling approach. Users can interactively generate various crystal clusters, including amethyst and citrine clusters. Furthermore, our approach offers a high-level specification, i.e., target shape so that the generated clusters approximate the shape; such controllability is crucial for realizing artists’ intentions. Additionally, we focused on fabrication-oriented procedural modeling. We identify the possible parameter spaces based on physical experiments, i.e., test the removability of resin casts from silicone molds produced by the 3D printed crystal clusters for making replicas.

This paper presents a novel approach to simulating surface tension flow within a position-based dynamics (PBD) framework. We enhance the conventional PBD fluid method in terms of its surface representation and constraint enforcement to furnish support for the simulation of interfacial phenomena driven by strong surface tension and contact dynamics. The key component of our framework is an on-the-fly local meshing algorithm to build the local geometry around each surface particle. Based on this local mesh structure, we devise novel surface constraints that can be integrated seamlessly into a PBD framework to model strong surface tension effects. We demonstrate the efficacy of our approach by simulating a multitude of surface tension flow examples exhibiting intricate interfacial dynamics of films and drops, which were all infeasible for a traditional PBD method.

StageMix is a mixed video that is created by concatenating the segments from various performance videos of an identical song in a visually smooth manner by matching the main subject's silhouette presented in the frame. We introduce PopStage, which allows users to generate a StageMix automatically. PopStage is designed based on the StageMix Editing Guideline that we established by interviewing creators as well as observing their workflows. PopStage consists of two main steps: finding an editing path and generating a transition effect at a transition point. Using a reward function that favors visual connection and the optimality of transition timing across the videos, we obtain the optimal path that maximizes the sum of rewards through dynamic programming. Given the optimal path, PopStage then aligns the silhouettes of the main subject from the transitioning video pair to enhance the visual connection at the transition point. The virtual camera view is next optimized to remove the black areas that are often created due to the transformation needed for silhouette alignment, while reducing pixel loss. In this process, we enforce the view to be the maximum size while maintaining the temporal continuity across the frames. Experimental results show that PopStage can generate a StageMix of a similar quality to those produced by professional creators in a highly reduced production time.

Single view-based reconstruction of hand-object interaction is challenging due to the severe observation missing caused by occlusions. This paper proposes a physics-based method to better solve the ambiguities in the reconstruction. It first proposes a force-based dynamic model of the in-hand object, which not only recovers the unobserved contacts but also solves for plausible contact forces. Next, a confidence-based slide prevention scheme is proposed, which combines both the kinematic confidences and the contact forces to jointly model static and sliding contact motion. Qualitative and quantitative experiments show that the proposed technique reconstructs both physically plausible and more accurate hand-object interaction and estimates plausible contact forces in real-time with a single RGBD sensor.