This paper presents a computational pipeline for creating personalized, physical LEGO®1 figurines from user-input portrait photos. The generated figurine is an assembly of coherently-connected LEGO® bricks detailed with uv-printed decals, capturing prominent features such as hairstyle, clothing style, and garment color, and also intricate details such as logos, text, and patterns. This task is non-trivial, due to the substantial domain gap between unconstrained user photos and the stylistically-consistent LEGO® figurine models. To ensure assemble-ability by LEGO® bricks while capturing prominent features and intricate details, we design a three-stage pipeline: (i) we formulate a CLIP-guided retrieval approach to connect the domains of user photos and LEGO® figurines, then output physically-assemble-able LEGO® figurines with decals excluded; (ii) we then synthesize decals on the figurines via a symmetric U-Nets architecture conditioned on appearance features extracted from user photos; and (iii) we next reproject and uv-print the decals on associated LEGO® bricks for physical model production. We evaluate the effectiveness of our method against eight hundred expert-designed figurines, using a comprehensive set of metrics, which include a novel GPT-4V-based evaluation metric, demonstrating superior performance of our method in visual quality and resemblance to input photos. Also, we show our method's robustness by generating LEGO® figurines from diverse inputs and physically fabricating and assembling several of them.
论文检索
输入标题、作者或关键词，从 252 篇学术成果中精准定位
Illusion-knit fabrics reveal distinct patterns or images depending on the viewing angle. Artists have manually achieved this effect by exploiting "microgeometry," i.e., small differences in stitch heights. However, past work in computational 3D knitting does not model or exploit designs based on stitch height variation. This paper establishes a foundation for exploring illusion knitting in the context of computational design and fabrication. We observe that the design space is highly constrained, elucidate these constraints, and derive strategies for developing effective, machine-knittable illusion patterns. We partially automate these strategies in a new interactive design tool that reduces difficult patterning tasks to familiar image editing tasks. Illusion patterns also uncover new fabrication challenges regarding mixed colorwork and texture; we describe new algorithms for mitigating fabrication failures and ensuring high-quality knit results.
We present a sensor that can measure light and wirelessly communicate the measurement, without the need for an external power source or a battery. Our sensor, called cricket, harvests energy from incident light. It is asleep for most of the time and transmits a short and strong radio frequency chirp when its harvested energy reaches a specific level. The carrier frequency of each cricket is fixed and reveals its identity, and the duration between consecutive chirps is a measure of the incident light level. We have characterized the radiometric response function, signal-to-noise ratio and dynamic range of cricket. We have experimentally verified that cricket can be miniaturized at the expense of increasing the duration between chirps. We show that a cube with a cricket on each of its sides can be used to estimate the centroid of any complex illumination, which has value in applications such as solar tracking. We also demonstrate the use of crickets for creating untethered sensor arrays that can produce video and control lighting for energy conservation. Finally, we modified cricket's circuit to develop battery-free electronic sunglasses that can instantly adapt to environmental illumination.
TensoSDF: Roughness-aware Tensorial Representation for Robust Geometry and Material Reconstruction
PDF ↗Reconstructing objects with realistic materials from multi-view images is problematic, since it is highly ill-posed. Although the neural reconstruction approaches have exhibited impressive reconstruction ability, they are designed for objects with specific materials (e.g., diffuse or specular materials). To this end, we propose a novel framework for robust geometry and material reconstruction, where the geometry is expressed with the implicit signed distance field (SDF) encoded by a tensorial representation, namely TensoSDF. At the core of our method is the roughness-aware incorporation of the radiance and reflectance fields, which enables a robust reconstruction of objects with arbitrary reflective materials. Furthermore, the tensorial representation enhances geometry details in the reconstructed surface and reduces the training time. Finally, we estimate the materials using an explicit mesh for efficient intersection computation and an implicit SDF for accurate representation. Consequently, our method can achieve more robust geometry reconstruction, outperform the previous works in terms of relighting quality, and reduce 50% training times and 70% inference time. Codes and datasets are available at https://github.com/Riga2/TensoSDF.
While surface-based view synthesis algorithms are appealing due to their low computational requirements, they often struggle to reproduce thin structures. In contrast, more expensive methods that model the scene's geometry as a volumetric density field (e.g. NeRF) excel at reconstructing fine geometric detail. However, density fields often represent geometry in a "fuzzy" manner, which hinders exact localization of the surface. In this work, we modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. First, we employ a discrete opacity grid representation instead of a continuous density field, which allows opacity values to discontinuously transition from zero to one at the surface. Second, we anti-alias by casting multiple rays per pixel, which allows occlusion boundaries and subpixel structures to be modelled without using semi-transparent voxels. Third, we minimize the binary entropy of the opacity values, which facilitates the extraction of surface geometry by encouraging opacity values to binarize towards the end of training. Lastly, we develop a fusion-based meshing strategy followed by mesh simplification and appearance model fitting. The compact meshes produced by our model can be rendered in real-time on mobile devices and achieve significantly higher view synthesis quality compared to existing mesh-based approaches. Our interactive webdemo is available at https://binary-opacity-grid.github.io.
Neural Radiance Fields (NeRF) achieves unprecedented performance in synthesizing novel view synthesis, utilizing multi-view consistency. When capturing multiple inputs, image signal processing (ISP) in modern cameras will independently enhance them, including exposure adjustment, color correction, local tone mapping, etc. While these processings greatly improve image quality, they often break the multi-view consistency assumption, leading to "floaters" in the reconstructed radiance fields. To address this concern without compromising visual aesthetics, we aim to first disentangle the enhancement by ISP at the NeRF training stage and re-apply user-desired enhancements to the reconstructed radiance fields at the finishing stage. Furthermore, to make the re-applied enhancements consistent between novel views, we need to perform imaging signal processing in 3D space (i.e. "3D ISP"). For this goal, we adopt the bilateral grid, a locally-affine model, as a generalized representation of ISP processing. Specifically, we optimize per-view 3D bilateral grids with radiance fields to approximate the effects of camera pipelines for each input view. To achieve user-adjustable 3D finishing, we propose to learn a low-rank 4D bilateral grid from a given single view edit, lifting photo enhancements to the whole 3D scene. We demonstrate our approach can boost the visual quality of novel view synthesis by effectively removing floaters and performing enhancements from user retouching. The source code and our data are available at: https://bilarfpro.github.io.
We introduce a fast, robust, and user-controllable algorithm to generate surface-filling curves. We compute these curves through the gradient flow of a simple sparse energy, making our method several orders of magnitude faster than previous works. Our algorithm makes minimal assumptions on the topology and resolution of the input surface, achieving improved robustness. Our framework provides tuneable parameters that guide the shape of the output curve, making it ideal for interactive design applications.
Generating realistic models of trees and plants is a complex problem because of the vast variety of shapes trees can form. Procedural modeling algorithms are popular for defining branching structures and steadily increasing their expressive power by considering more biological findings. Most existing methods focus on defining the branching structure of trees based on skeletal graphs, while the surface mesh of branches is most commonly defined as simple cylinders. One critical open problem is defining and controlling the complex details observed in real trees. This paper aims to advance tree modeling by proposing a strand-based volumetric representation for tree models. Strands are fixed-size volumetric pipes that define the branching structure. By leveraging strands, our approach captures the lateral development of trees. We combine the strands with a novel branch development formulation that allows us to locally inject vigor and reshape the tree model. Moreover, we define a set of editing operators for tree primary and lateral development that enables users to interactively generate complex tree models with unprecedented detail with minimal effort.
Modeling high-resolution terrains is a perennial challenge in the creation of virtual worlds. In this paper, we focus on the amplification of a low-resolution input terrain into a high-resolution, hydrologically consistent terrain featuring complex patterns by a multi-scale approach. Our framework combines the best of both worlds, relying on physics-inspired erosion models producing consistent erosion landmarks and introducing control at different scales, thus bridging the gap between physics-based erosion simulations and multi-scale procedural modeling. The method uses a fast and accurate approximation of different simulations, including thermal, stream power erosion and deposition performed at different scales to obtain a range of effects. Our approach provides landscape designers with tools for amplifying mountain ranges and valleys with consistent details.
In this work, we present MoConVQ, a novel unified framework for physics-based motion control leveraging scalable discrete representations. Building upon vector quantized variational autoencoders (VQ-VAE) and model-based reinforcement learning, our approach effectively learns motion embeddings from a large, unstructured dataset spanning tens of hours of motion examples. The resultant motion representation not only captures diverse motion skills but also offers a robust and intuitive interface for various applications. We demonstrate the versatility of MoConVQ through several applications: universal tracking control from various motion sources, interactive character control with latent motion representations using supervised learning, physics-based motion generation from natural language descriptions using the GPT framework, and, most interestingly, seamless integration with large language models (LLMs) with in-context learning to tackle complex and abstract tasks.
Real-time character control is an essential component for interactive experiences, with a broad range of applications, including physics simulations, video games, and virtual reality. The success of diffusion models for image synthesis has led to the use of these models for motion synthesis. However, the majority of these motion diffusion models are primarily designed for offline applications, where space-time models are used to synthesize an entire sequence of frames simultaneously with a pre-specified length. To enable real-time motion synthesis with diffusion model that allows time-varying controls, we propose A-MDM (Auto-regressive Motion Diffusion Model). Our conditional diffusion model takes an initial pose as input, and auto-regressively generates successive motion frames conditioned on the previous frame. Despite its streamlined network architecture, which uses simple MLPs, our framework is capable of generating diverse, long-horizon, and high-fidelity motion sequences. Furthermore, we introduce a suite of techniques for incorporating interactive controls into A-MDM, such as task-oriented sampling, in-painting, and hierarchical reinforcement learning (See Figure 1). These techniques enable a pre-trained A-MDM to be efficiently adapted for a variety of new downstream tasks. We conduct a comprehensive suite of experiments to demonstrate the effectiveness of A-MDM, and compare its performance against state-of-the-art auto-regressive methods.
Translating motions from a real user onto a virtual embodied avatar is a key challenge for character animation in the metaverse. In this work, we present a novel generative framework that enables mapping from a set of sparse sensor signals to a full body avatar motion in real-time while faithfully preserving the motion context of the user. In contrast to existing techniques that require training a motion prior and its mapping from control to motion separately, our framework is able to learn the motion manifold as well as how to sample from it at the same time in an end-to-end manner. To achieve that, we introduce a technique called codebook matching which matches the probability distribution between two categorical codebooks for the inputs and outputs for synthesizing the character motions. We demonstrate this technique can successfully handle ambiguity in motion generation and produce high quality character controllers from unstructured motion capture data. Our method is especially useful for interactive applications like virtual reality or video games where high accuracy and responsiveness are needed.
While conventional cameras offer versatility for applications ranging from amateur photography to autonomous driving, computational cameras allow for domain-specific adaption. Cameras with co-designed optics and image processing algorithms enable high-dynamic-range image recovery, depth estimation, and hyperspectral imaging through optically encoding scene information that is otherwise undetected by conventional cameras. However, this optical encoding creates a challenging inverse reconstruction problem for conventional image recovery, and often lowers the overall photographic quality. Thus computational cameras with domain-specific optics have only been adopted in a few specialized applications where the captured information cannot be acquired in other ways. In this work, we investigate a method that combines two optical systems into one to tackle this challenge. We split the aperture of a conventional camera into two halves: one which applies an application-specific modulation to the incident light via a diffractive optical element to produce a coded image capture, and one which applies no modulation to produce a conventional image capture. Co-designing the phase modulation of the split aperture with a dual-pixel sensor allows us to simultaneously capture these coded and uncoded images without increasing physical or computational footprint. With an uncoded conventional image alongside the optically coded image in hand, we investigate image reconstruction methods that are conditioned on the conventional image, making it possible to eliminate artifacts and compute costs that existing methods struggle with. We assess the proposed method with 2-in-1 cameras for optical high-dynamic-range reconstruction, monocular depth estimation, and hyperspectral imaging, comparing favorably to all tested methods in all applications.
This paper develops a shape space framework for collision-aware geometric modeling, where basic geometric operations automatically avoid inter-penetration. Shape spaces are a powerful tool for surface modeling, shape analysis, nonrigid motion planning, and animation, but past formulations permit nonphysical intersections. Our framework augments an existing shape space using a repulsive energy such that collision avoidance becomes a first-class property, encoded in the Riemannian metric itself. In turn, tasks like intersection-free shape interpolation or motion extrapolation amount to simply computing geodesic paths via standard numerical algorithms. To make optimization practical, we develop an adaptive collision penalty that prevents mesh self-intersection, and converges to a meaningful limit energy under refinement. The final algorithms apply to any category of shape, and do not require a dataset of examples, training, rigging, nor any other prior information. For instance, to interpolate between two shapes we need only a single pair of meshes with the same connectivity. We evaluate our method on a variety of challenging examples from modeling and animation.
In this paper, we introduce a novel approach for computing conformal deformations in ℝ3 while minimizing curvature-based energies. Curvature-based energies serve as fundamental tools in geometry processing, essential for tasks such as surface fairing, deformation, and approximation using developable or cone metric surfaces. However, accurately computing the geometric embedding, especially for the latter, has been a challenging endeavor. The complexity arises from inherent numerical instabilities in curvature estimation and the intricate nature of differentiating these energies. To address these challenges, we concentrate on conformal deformations, leveraging the curvature tensor as the primary variable in our model. This strategic choice renders curvature-based energies easily applicable, mitigating previous manipulation difficulties. Our key contribution lies in identifying a previously unknown integrability condition that establishes a connection between conformal deformations and changes in curvature. We use this insight to deform surfaces of arbitrary genus, aiming to minimize bending energies or prescribe Gaussian curvature while sticking to positional constraints.
As a natural extension to the harmonic coordinates, the biharmonic coordinates have been found superior for planar shape and image manipulation with an enriched deformation space. However, the 3D biharmonic coordinates and their derivatives have remained unexplored. In this work, we derive closed-form expressions for biharmonic coordinates and their derivatives for 3D triangular cages. The core of our derivation lies in computing the closed-form expressions for the integral of the Euclidean distance over a triangle and its derivatives. The derived 3D biharmonic coordinates not only fill a missing component in methods of generalized barycentric coordinates but also pave the way for various interesting applications in practice, including producing a family of biharmonic deformations, solving variational shape deformations, and even unlocking the closed-form expressions for recently-introduced Somigliana coordinates for both fast and accurate evaluations.
Procedural animation has seen widespread use in the design of expressive walking gaits for virtual characters. While similar tools could breathe life into robotic characters, existing techniques are largely unaware of the kinematic and dynamic constraints imposed by physical robots. In this paper, we propose a system for the artist-directed authoring of stylized bipedal walking gaits, tailored for execution on robotic characters. The artist interfaces with an interactive editing tool that generates the desired character motion in realtime, either on the physical or simulated robot, using a model-based control stack. Each walking style is encoded as a set of sample parameters which are translated into whole-body reference trajectories using the proposed procedural animation technique. In order to generalize the stylized gait over a continuous range of input velocities, we employ a phase-space blending strategy that interpolates a set of example walk cycles authored by the animator while preserving contact constraints. To demonstrate the utility of our approach, we animate gaits for a custom, free-walking robotic character, and show, with two additional in-simulation examples, how our procedural animation technique generalizes to bipeds with different degrees of freedom, proportions, and mass distributions.
In this work, we present Semantic Gesticulator, a novel framework designed to synthesize realistic gestures accompanying speech with strong semantic correspondence. Semantically meaningful gestures are crucial for effective non-verbal communication, but such gestures often fall within the long tail of the distribution of natural human motion. The sparsity of these movements makes it challenging for deep learning-based systems, trained on moderately sized datasets, to capture the relationship between the movements and the corresponding speech semantics. To address this challenge, we develop a generative retrieval framework based on a large language model. This framework efficiently retrieves suitable semantic gesture candidates from a motion library in response to the input speech. To construct this motion library, we summarize a comprehensive list of commonly used semantic gestures based on findings in linguistics, and we collect a high-quality motion dataset encompassing both body and hand movements. We also design a novel GPT-based model with strong generalization capabilities to audio, capable of generating high-quality gestures that match the rhythm of speech. Furthermore, we propose a semantic alignment mechanism to efficiently align the retrieved semantic gestures with the GPT's output, ensuring the naturalness of the final animation. Our system demonstrates robustness in generating gestures that are rhythmically coherent and semantically explicit, as evidenced by a comprehensive collection of examples. User studies confirm the quality and human-likeness of our results, and show that our system outperforms state-of-the-art systems in terms of semantic appropriateness by a clear margin. We will release the code and dataset for academic research.
Recent advances in generative imagery have brought forth outpainting and inpainting models that can produce high-quality, plausible image content in unknown regions. However, the content these models hallucinate is necessarily inauthentic, since they are unaware of the true scene. In this work, we propose RealFill, a novel generative approach for image completion that fills in missing regions of an image with the content that should have been there. RealFill is a generative inpainting model that is personalized using only a few reference images of a scene. These reference images do not have to be aligned with the target image, and can be taken with drastically varying viewpoints, lighting conditions, camera apertures, or image styles. Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene. We evaluate RealFill on a new image completion benchmark that covers a set of diverse and challenging scenarios, and find that it outperforms existing approaches by a large margin. Project page: https://realfill.github.io.
Gaussian scale spaces are a cornerstone of signal representation and processing, with applications in filtering, multiscale analysis, anti-aliasing, and many more. However, obtaining such a scale space is costly and cumbersome, in particular for continuous representations such as neural fields. We present an efficient and lightweight method to learn the fully continuous, anisotropic Gaussian scale space of an arbitrary signal. Based on Fourier feature modulation and Lipschitz bounding, our approach is trained self-supervised, i.e., training does not require any manual filtering. Our neural Gaussian scale-space fields faithfully capture multiscale representations across a broad range of modalities, and support a diverse set of applications. These include images, geometry, light-stage data, texture anti-aliasing, and multiscale optimization.