SIGGRAPH 2022 论文列表

Repetitive vector patterns are common in a variety of applications but can be challenging and tedious to create. Existing automatic synthesis methods target relatively simple, unstructured patterns such as discrete elements and continuous Bézier curves. This paper proposes an algorithm for generating vector patterns with diverse shapes and structured local interactions via a sample-based representation. Our main idea is adding explicit clustering as part of neighborhood similarity and iterative sample optimization for more robust sample synthesis and pattern reconstruction. The results indicate that our method can outperform existing methods on synthesizing a variety of structured vector textures. Our project page is available at https://phtu-cs.github.io/cvt-sig22/.

Enabling additive manufacturing to employ a wide range of novel, functional materials can be a major boost to this technology. However, making such materials printable requires painstaking trial-and-error by an expert operator, as they typically tend to exhibit peculiar rheological or hysteresis properties. Even in the case of successfully finding the process parameters, there is no guarantee of print-to-print consistency due to material differences between batches. These challenges make closed-loop feedback an attractive option where the process parameters are adjusted on-the-fly. There are several challenges for designing an efficient controller: the deposition parameters are complex and highly coupled, artifacts occur after long time horizons, simulating the deposition is computationally costly, and learning on hardware is intractable. In this work, we demonstrate the feasibility of learning a closed-loop control policy for additive manufacturing using reinforcement learning. We show that approximate, but efficient, numerical simulation is sufficient as long as it allows learning the behavioral patterns of deposition that translate to real-world experiences. In combination with reinforcement learning, our model can be used to discover control policies that outperform baseline controllers. Furthermore, the recovered policies have a minimal sim-to-real gap. We showcase this by applying our control policy in-vivo on a single-layer printer using low and high viscosity materials.

Computer animation relies heavily on rigging setups that articulate character surfaces through a broad range of poses. Although many deformation strategies have been proposed over the years, constructing character rigs is still a cumbersome process that involves repetitive authoring of point weights and corrective sculpts with limited and indirect shaping controls. This paper presents a new approach for character articulation that produces detail-preserving deformations fully controlled by 3D curves that profile the deforming surface. Our method starts with a spline-based rigging system in which artists can draw and articulate sparse curvenets that describe surface profiles. By analyzing the layout of the rigged curvenets, we quantify the deformation along each curve side independent of the mesh connectivity, thus separating the articulation controllers from the underlying surface representation. To propagate the curvenet articulation over the character surface, we formulate a deformation optimization that reconstructs surface details while conforming to the rigged curvenets. In this process, we introduce a cut-cell algorithm that binds the curvenet to the surface mesh by cutting mesh elements into smaller polygons possibly with cracks, and then derive a cut-aware numerical discretization that provides harmonic interpolations with curve discontinuities. We demonstrate the expressiveness and flexibility of our method using a series of animation clips.

Depth sensors have emerged as a cornerstone sensor modality with diverse applications in personal hand-held devices, robotics, scientific imaging, autonomous vehicles, and more. In particular, correlation Time-of-Flight (ToF) sensors have found widespread adoption for meter-scale indoor applications such as object tracking and pose estimation. While they offer high depth resolution at competitive costs, the precision of these indirect ToF sensors is fundamentally limited by their modulation contrast, which is in turn limited by the effects of photo-conversion noise. In contrast, optical interferometric methods can leverage short illumination modulation wavelengths to achieve depth precision three orders of magnitude greater than ToF, but typically find their range is restricted to the sub-centimeter. In this work, we merge concepts from both correlation ToF design and interferometric imaging; a step towards bridging the gap between these methods. We propose a computational ToF imaging method that optically computes the GHz ToF correlation signal in free space before photo-conversion. To acquire a depth map, we scan a scene point-wise and computationally unwrap the collected correlation measurements. Specifically, we repurpose electro-optical modulators used in optical communication for ToF imaging with centimeter-wave signals, and achieve all-optical correlation at 7.15 GHz and 14.32 GHz modulation frequencies. While GHz modulation frequencies increase depth precision, these high modulation rates also pose a technical challenge. They result in dozens of wraps per meter which cannot be estimated robustly by existing phase unwrapping methods. We tackle this problem with a proposed segmentation-inspired phase unwrapping network, which exploits the correlation of adjacent GHz phase measurements to classify regions into their respective wrap counts. We validate this method in simulation and experimentally, and demonstrate precise depth sensing using centimeter wave modulation that is robust to surface texture and ambient light. Compared to existing analog demodulation methods, the proposed system outperforms all of them across all tested scenarios. CCS Concepts: • Computing methodologies;

The success of StyleGAN has enabled unprecedented semantic editing capabilities, on both synthesized and real images. However, such editing operations are either trained with semantic supervision or annotated manually by users. In another development, the CLIP architecture has been trained with internet-scale loose image and text pairings, and has been shown to be useful in several zero-shot learning settings. In this work, we investigate how to effectively link the pretrained latent spaces of StyleGAN and CLIP, which in turn allows us to automatically extract semantically-labeled edit directions from StyleGAN, finding and naming meaningful edit operations, in a fully unsupervised setup, without additional human guidance. Technically, we propose two novel building blocks; one for discovering interesting CLIP directions and one for semantically labeling arbitrary directions in CLIP latent space. The setup does not assume any pre-determined labels and hence we do not require any additional supervised text/attributes to build the editing framework. We evaluate the effectiveness of the proposed method and demonstrate that extraction of disentangled labeled StyleGAN edit directions is indeed possible, revealing interesting and non-trivial edit directions.

Diversity among agents’ behaviors and heterogeneity in virtual crowds in general, is an important aspect of crowd simulation as it is crucial to the perceived realism and plausibility of the resulting simulations. Heterogeneous crowds constitute the pillar in creating numerous real-life scenarios such as museum exhibitions, which require variety in agent behaviors, from basic collision avoidance to more complex interactions both among agents and with environmental features. Most of the existing systems optimize for specific behaviors such as goal seeking, and neglect to take into account other behaviors and how these interact together to form diverse agent profiles. In this paper, we present a RL-based framework for learning multiple agent behaviors concurrently. We optimize the agent policy by varying the importance of the selected behaviors (goal seeking, collision avoidance, interaction with environment, and grouping) while training; essentially we have a reward function that changes dynamically during training. The importance of each separate sub-behavior is added as input to the policy, resulting in the development of a single model capable of capturing as well as enabling dynamic run-time manipulation of agent profiles; thus allowing configurable profiles. Through a series of experiments, we verify that our system provides users with the ability to design virtual scenes; control and mix agent behaviors thus creating personality profiles, and assign different profiles to groups of agents. Moreover, we demonstrate that interestingly the proposed model generalizes to situations not seen in the training data such as a) crowds with higher density, b) behavior weights that are outside the training intervals and c) to scenes with more intricate environment layouts. Code, data and trained policies for this paper are at https://github.com/veupnea/CCP.

ACM Reference Format: Mikihito Matsuura, Koya Narumi, Toshiki Aoki, Yuta Noma, Kazutaka Nakashima, Yoshihiro Kawahara, and Takeo Igarashi. 2022. Blow-up Print: Rapidly 3D Printing Inflatable Objects in the Compressed State. In Special Interest Group on Computer Graphics and Interactive Techniques Conference Posters (SIGGRAPH ’22 Posters), August 07-11, 2022. ACM, New York, NY, USA, 2 pages. https://doi.org/10.1145/3532719.3543230

With the resurgence of non-contact vital sign sensing due to the COVID-19 pandemic, remote heart-rate monitoring has gained significant prominence. Many existing methods use cameras; however previous work shows a performance loss for darker skin tones. In this paper, we show through light transport analysis that the camera modality is fundamentally biased against darker skin tones. We propose to reduce this bias through multi-modal fusion with a complementary and fairer modality - radar. Through a novel debiasing oriented fusion framework, we achieve performance gains over all tested baselines and achieve skin tone fairness improvements over the RGB modality. That is, the associated Pareto frontier between performance and fairness is improved when compared to the RGB modality. In addition, performance improvements are obtained over the radar-based method, with small trade-offs in fairness. We also open-source the largest multi-modal remote heart-rate estimation dataset of paired camera and radar measurements with a focus on skin tone representation.

3D avatar creation plays a crucial role in the digital age. However, the whole production process is prohibitively time-consuming and labor-intensive. To democratize this technology to a larger audience, we propose AvatarCLIP, a zero-shot text-driven framework for 3D avatar generation and animation. Unlike professional software that requires expert knowledge, AvatarCLIP empowers layman users to customize a 3D avatar with the desired shape and texture, and drive the avatar with the described motions using solely natural languages. Our key insight is to take advantage of the powerful vision-language model CLIP for supervising neural human generation, in terms of 3D geometry, texture and animation. Specifically, driven by natural language descriptions, we initialize 3D human geometry generation with a shape VAE network. Based on the generated 3D human shapes, a volume rendering model is utilized to further facilitate geometry sculpting and texture generation. Moreover, by leveraging the priors learned in the motion VAE, a CLIP-guided reference-based motion synthesis method is proposed for the animation of the generated 3D avatar. Extensive qualitative and quantitative experiments validate the effectiveness and generalizability of AvatarCLIP on a wide range of avatars. Remarkably, AvatarCLIP can generate unseen 3D avatars with novel animations, achieving superior zero-shot capability. Codes are available at https://github.com/hongfz16/AvatarCLIP.

Quantization has proven effective in high-resolution and large-scale simulations, which benefit from bit-level memory saving. However, identifying a quantization scheme that meets the requirement of both precision and memory efficiency requires trial and error. In this paper, we propose a novel framework to allow users to obtain a quantization scheme by simply specifying either an error bound or a memory compression rate. Based on the error propagation theory, our method takes advantage of auto-diff to estimate the contributions of each quantization operation to the total error. We formulate the task as a constrained optimization problem, which can be efficiently solved with analytical formulas derived for the linearized objective function. Our workflow extends the Taichi compiler and introduces dithering to improve the precision of quantized simulations. We demonstrate the generality and efficiency of our method via several challenging examples of physics-based simulation, which achieves up to 2.5× memory compression without noticeable degradation of visual quality in the results. Our code and data are available at https://github.com/Hanke98/AutoQantizer.

Creating photorealistic avatars of existing people currently requires extensive person-specific data capture, which is usually only accessible to the VFX industry and not the general public. Our work aims to address this drawback by relying only on a short mobile phone capture to obtain a drivable 3D head avatar that matches a person's likeness faithfully. In contrast to existing approaches, our architecture avoids the complex task of directly modeling the entire manifold of human appearance, aiming instead to generate an avatar model that can be specialized to novel identities using only small amounts of data. The model dispenses with low-dimensional latent spaces that are commonly employed for hallucinating novel identities, and instead, uses a conditional representation that can extract person-specific information at multiple scales from a high resolution registered neutral phone scan. We achieve high quality results through the use of a novel universal avatar prior that has been trained on high resolution multi-view video captures of facial performances of hundreds of human subjects. By fine-tuning the model using inverse rendering we achieve increased realism and personalize its range of motion. The output of our approach is not only a high-fidelity 3D head avatar that matches the person's facial shape and appearance, but one that can also be driven using a jointly discovered shared global expression space with disentangled controls for gaze direction. Via a series of experiments we demonstrate that our avatars are faithful representations of the subject's likeness. Compared to other state-of-the-art methods for lightweight avatar creation, our approach exhibits superior visual quality and animateability.

Figure 1: Spatiotemporal layout of the presented experiment. (a) Spatial layout of the experiments. There were three possible locations of the visual targets (which subtended a visual angle of one degree) inside the participant’s field of view (FoV). Auditory stimuli were spatially located outside the FoV. Both the visual targets and the auditory stimuli moved in solidarity with the participant’s head. One possible combination for an audiovisual stimuli is highlighted in blue. (b) Temporal layout. Visual targets were shown 100 ms after the sound started, for a duration of 24 ms. The auditory stimulus lasted 400 ms in order for the more complex sounds to be played completely. (c) Representative close-up view of the virtual environment. The inset shows five different visual targets (a 3.2x scale is used here for visualization purposes). Participants could freely move in a physical space of 4x1.5m. Scene by Barking Dog for Unity 3D. Six different sounds were used: white noise, pink noise, brown noise, pure frequencies, train horn and human voice.

This paper presents an audio-to-animation synthesis method for violin performance. This new approach provides a fine-grained violin performance animation using information on playing procedure consisting of played string, finger number, position, and bow direction. We demonstrate that our method is capable of synthesizing natural violin performance animation with fine fingering and bowing through extensive evaluation.

When an object breaks, simulating evolution of fracture as per artist control while maintaining physical realism and plausibility is a challenging problem due to different complex material properties of real world objects. In this work, we present impurity maps as a way to guide fracture paths for both brittle and ductile fracture. We develop a novel probabilistic damage mechanics to model fracture in materials with impurities, using a random graph-based formulation in conjunction with graph-based FEM. An artist created map allows us to selectively distribute the impurities in the material, to weaken the object in those specific regions where the imperfections are added. During simulation, the presence of impurities guide the cracks that develop such that the fracture pattern closely follows the impurity map. We simulate artist-controlled fractures on different materials to demonstrate the potency of our method.