Photorealistic 3D head avatar reconstruction faces critical challenges in modeling dynamic face-hair interactions and achieving cross-identity generalization, particularly during expressions and head movements. We present LUCAS, a novel Universal Prior Model (UPM) for codec avatar modeling that disentangles face and hair through a layered representation. Unlike previous UPMs that treat hair as an integral part of the head, our approach separates the modeling of the hairless head and hair into distinct branches. LUCAS is the first to introduce a mesh-based UPM, facilitating real-time rendering on devices. Our layered representation also improves the anchor geometry for precise and visually appealing Gaussian renderings. Experimental results indicate that LUCAS outperforms existing single-mesh and Gaussian-based avatar models in both quantitative and qualitative assessments, including evaluations on held-out subjects in zero-shot driving scenarios. LUCAS demonstrates superior dynamic performance in managing head pose changes, expression transfer, and hairstyle variations, thereby advancing the state-of-the-art in 3D head avatar reconstruction. Project page: https://lsn33096.github.io/LUCAS/.

Recent 3D Instance Segmentation methods typically encode hundreds of instance-wise candidates with instance-specific information in various ways and refine them into final masks. However, they have yet to fully explore the benefit of these candidates. They overlook the valuable cues encoded in multiple candidates that represent different parts of the same instance, resulting in fragments. Also, they often fail to capture the precise spatial range of 3D instances, primarily due to inherent noises from sparse and unordered point clouds. In this work, to address these challenges, we propose IKNE, a novel instance-wise knowledge enhancement approach. We first introduce an Instance-wise Knowledge Aggregation (IKA) to associate scattered single instance details by optimizing correlations among candidates representing the same instance. Moreover, we present an Instance-wise Structural Guidance (ISG) to enhance the spatial understanding of candidates using structural cues from ambiguity-reduced features. Here, we utilize a simple yet effective truncated singular value decomposition algorithm to minimize inherent noises of 3D features. In our extensive experiments on large-scale datasets, ScanNetV2, ScanNet200, S3DIS, and STPLS3D, IKNE outperforms existing works. We validate the effectiveness of our modules in both kernel-based and transformer-based architectures.

Inverse rendering aims to reconstruct geometry and reflectance from captured images. Display-camera imaging systems offer unique advantages for this task: each pixel can easily function as a programmable point light source, and the polarized light emitted by LCD displays facilitates diffuse-specular separation. Despite these benefits, there is currently no public real-world dataset captured using display-camera systems, unlike other setups such as light stages. This absence hinders the development and evaluation of display-based inverse rendering methods. In this paper, we introduce the first real-world dataset for display-based inverse rendering. To achieve this, we construct and calibrate an imaging system comprising an LCD display and stereo polarization cameras. We then capture a diverse set of objects with diverse geometry and reflectance under one-light-at-a-time (OLAT) display patterns. We also provide high-quality ground-truth geometry. Our dataset enables the synthesis of captured images under arbitrary display patterns and different noise levels. Using this dataset, we evaluate the performance of existing photometric stereo and inverse rendering methods, and provide a simple, yet effective baseline for display inverse rendering, outperforming state-of-the-art inverse rendering methods. Code and dataset are available on our project page at https://michaelcsj.github.io/DIR/

We present 3DGH, an unconditional generative model for 3D human heads with composable hair and face components. Unlike previous work that entangles the modeling of hair and face, we propose to separate them using a novel data representation with template-based 3D Gaussian Splatting, in which deformable hair geometry is introduced to capture the geometric variations across different hairstyles. Based on this data representation, we design a 3D GAN-based architecture with dual generators and employ a cross-attention mechanism to model the inherent correlation between hair and face. The model is trained on synthetic renderings using carefully designed objectives to stabilize training and facilitate hair-face separation. We conduct extensive experiments to validate the design choice of 3DGH, and evaluate it both qualitatively and quantitatively by comparing with several state-of-the-art 3D GAN methods, demonstrating its effectiveness in unconditional full-head image synthesis and composable 3D hairstyle editing. More details will be available on our project page: https://c-he.github.io/projects/3dgh/.

Hair plays a significant role in personal identity and appearance, making it an essential component of high-quality, photorealistic avatars. Existing approaches either focus on modeling the facial region only or rely on personalized models, limiting their generalizability and scalability. In this paper, we present a novel method for creating high-fidelity avatars with diverse hairstyles. Our method leverages the local similarity across different hairstyles and learns a universal hair appearance prior from multi-view captures of hundreds of people. This prior model takes 3D-aligned features as input and generates dense radiance fields conditioned on a sparse point cloud with color. As our model splits different hairstyles into local primitives and builds prior at that level, it is capable of handling various hair topologies. Through experiments, we demonstrate that our model captures a diverse range of hairstyles and generalizes well to challenging new hairstyles. Empirical results show that our method improves the state-of-the-art approaches in capturing and generating photorealistic, personalized avatars with complete hair.

Photometric stereo leverages variations in illumination conditions to reconstruct surface normals. Display photo-metric stereo, which employs a conventional monitor as an illumination source, has the potential to overcome limitations often encountered in bulky and difficult-to-use conventional setups. In this paper, we present differentiable display photometric stereo (DDPS), addressing an often overlooked challenge in display photometric stereo: the design of display patterns. Departing from using heuristic display patterns, DDPS learns the display patterns that yield accurate normal reconstruction for a target system in an end-to-end manner. To this end, we propose a differentiable framework that couples basis-illumination image formation with analytic photometric-stereo reconstruction. The differentiable framework facilitates the effective learning of display patterns via auto-differentiation. Also, for training supervision, we propose to use 3D printing for creating a real-world training dataset, enabling accurate reconstruction on the target real-world setup. Finally, we exploit that conventional LCD monitors emit polarized light, which allows for the optical separation of diffuse and specular reflections when combined with a polarization camera, leading to accurate normal reconstruction. Extensive evaluation of DDPS shows improved normal-reconstruction accuracy compared to heuristic patterns and demonstrates compelling properties such as robustness to pattern initialization, calibration errors, and simplifications in image for-mation and reconstruction.

We present InterHandGen, a novel framework that learns the generative prior of two-hand interaction. Sampling from our model yields plausible and diverse two-hand shapes in close interaction with or without an object. Our prior can be incorporated into any optimization or learning methods to reduce ambiguity in an ill-posed setup. Our key observation is that directly modeling the joint distribution of multiple instances imposes high learning complexity due to its combinatorial nature. Thus, we propose to decom-pose the modeling of joint distribution into the modeling of factored unconditional and conditional single instance distribution. In particular, we introduce a diffusion model that learns the single-hand distribution unconditional and conditional to another hand via conditioning dropout. For sampling, we combine anti-penetration and classifier-free guidance to enable plausible generation. Furthermore, we establish the rigorous evaluation protocol of two-hand synthesis, where our method significantly outperforms baseline generative models in terms of plausibility and diversity. We also demonstrate that our diffusion prior can boost the performance of two-hand reconstruction from monocular in-the-wild images, achieving new state-of-the-art accuracy.

While recent 3D instance segmentation approaches show promising results based on transformer architectures, they often fail to correctly identify instances with similar appearances. They also ambiguously determine edges, leading to multiple misclassifications of adjacent edge points. In this work, we introduce a novel framework, called EASE, to overcome these challenges and improve the perception of complex 3D instances. We first propose a semantic guidance network to leverage rich semantic knowledge from a language model as intelligent priors, enhancing the functional understanding of real-world instances beyond relying solely on geometrical information. We explicitly instruct the basic instance queries using text embeddings of each instance to learn deep semantic details. Further, we utilize the edge prediction module, encouraging the segmentation network to be edge-aware. We extract voxel-wise edge maps from point features and use them as auxiliary information for learning edge cues. In our extensive experiments on large-scale benchmarks, ScanNetV2, ScanNet200, S3DIS, and STPLS3D, our EASE outperforms existing state-of-the-art models, demonstrating its superior performance.

The fidelity of relighting is bounded by both geometry and appearance representations. For geometry, both mesh and volumetric approaches have difficulty modeling intri-cate structures like 3D hair geometry. For appearance, existing relighting models are limited in fidelity and often too slow to render in real-time with high-resolution contin-uous environments. In this work, we present Relightable Gaussian Codec Avatars, a method to build high-fidelity relightable head avatars that can be animated to generate novel expressions. Our geometry model based on 3D Gaus-sians can capture 3D-consistent sub-millimeter details such as hair strands and pores on dynamic face sequences. To support diverse materials of human heads such as the eyes, skin, and hair in a unified manner, we present a novel re-lightable appearance model based on learnable radiance transfer. Together with global illumination-aware spheri-cal harmonics for the diffuse components, we achieve real-time relighting with all-frequency reflections using spheri-cal Gaussians. This appearance model can be efficiently relit under both point light and continuous illumination. We further improve the fidelity of eye reflections and enable ex-plicit gaze control by introducing relightable explicit eye models. Our method outperforms existing approaches with-out compromising real-time performance. We also demon-strate real-time relighting of avatars on a tethered con-sumer VR headset, showcasing the efficiency and fidelity of our avatars.

We introduce a doubly hierarchical generative representation for strand-based 3D hairstyle geometry that progresses from coarse, low-pass filtered guide hair to densely populated hair strands rich in high-frequency details. We employ the Discrete Cosine Transform (DCT) to separate low-frequency structural curves from high-frequency curliness and noise, avoiding the Gibbs' oscillation issues associated with the standard Fourier transform in open curves. Unlike the guide hair sampled from the scalp UV map grids which may lose capturing details of the hairstyle in existing methods, our method samples optimal sparse guide strands by utilising $k$-medoids clustering centres from low-pass filtered dense strands, which more accurately retain the hairstyle's inherent characteristics. The proposed variational autoencoder-based generation network, with an architecture inspired by geometric deep learning and implicit neural representations, facilitates flexible, off-the-grid guide strand modelling and enables the completion of dense strands in any quantity and density, drawing on principles from implicit neural representations. Empirical evaluations confirm the capacity of the model to generate convincing guide hair and dense strands, complete with nuanced high-frequency details.

The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. Both problems are highly challenging, because hair has complex geometry and appearance and exhibits challenging motion. In this paper, we present a two-stage approach that models hair independently of the head to address these challenges in a data-driven manner. The first stage, state compression, learns a low-dimensional latent space of 3D hair states including motion and appearance via a novel autoencoder-as-a-tracker strategy. To better disentangle the hair and head in appearance learning, we employ multi-view hair segmentation masks in combination with a differentiable volumetric renderer. The second stage optimizes a novel hair dynamics model that performs temporal hair transfer based on the discovered latent codes. To enforce higher stability while driving our dynamics model, we employ the 3D point-cloud autoencoder from the compression stage for denoising of the hair state. Our model outperforms the state of the art in novel view synthesis and is capable of creating novel hair animations without relying on hair observations as a driving signal.††Project page at https://ziyanwl.github.io/neuwigs/.

Abstract Efficiently and accurately rendering hair accounting for multiple scattering is a challenging open problem. Path tracing in hair takes long to converge while other techniques are either too approximate while still being computationally expensive or make assumptions about the scene. We present a technique to infer the higher order scattering in hair in constant time within the path tracing framework, while achieving better computational efficiency. Our method makes no assumptions about the scene and provides control over the renderer's bias & speedup. We achieve this by training a small multilayer perceptron (MLP) to learn the higher‐order radiance online, while rendering progresses. We describe how to robustly train this network and thoroughly analyze our resulting renderer's characteristics. We evaluate our method on various hairstyles and lighting conditions. We also compare our method against a recent learning based & a traditional real‐time hair rendering method and demonstrate better quantitative & qualitative results. Our method achieves a significant improvement in speed with respect to path tracing, achieving a run‐time reduction of 40%‐70% while only introducing a small amount of bias.

We introduce CT2Hair, a fully automatic framework for creating high-fidelity 3D hair models that are suitable for use in downstream graphics applications. Our approach utilizes real-world hair wigs as input, and is able to reconstruct hair strands for a wide range of hair styles. Our method leverages computed tomography (CT) to create density volumes of the hair regions, allowing us to see through the hair unlike image-based approaches which are limited to reconstructing the visible surface. To address the noise and limited resolution of the input density volumes, we employ a coarse-to-fine approach. This process first recovers guide strands with estimated 3D orientation fields, and then populates dense strands through a novel neural interpolation of the guide strands. The generated strands are then refined to conform to the input density volumes. We demonstrate the robustness of our approach by presenting results on a wide variety of hair styles and conducting thorough evaluations on both real-world and synthetic datasets. Code and data for this paper are at github.com/facebookresearch/CT2Hair.

Capturing and rendering life-like hair is particularly challenging due to its fine geometric structure, the complex physical interaction and its non-trivial visual appearance. Yet, hair is a critical component for believable avatars. In this paper, we address the aforementioned problems: 1) we use a novel, volumetric hair representation that is composed of thousands of primitives. Each primitive can be rendered efficiently, yet realistically, by building on the latest advances in neural rendering. 2) To have a reliable control signal, we present a novel way of tracking hair on the strand level. To keep the computational effort manageable, we use guide hairs and classic techniques to expand those into a dense hood of hair. 3) To better enforce temporal consistency and generalization ability of our model, we further optimize the 3D scene flow of our representation with multiview optical flow, using volumetric raymarching. Our method can not only create realistic renders of recorded multi-view sequences, but also create renderings for new hair configurations by providing new control signals. We compare our method with existing work on viewpoint synthesis and drivable animation and achieve state-of-the-art results. https://ziyanw1.github.io/hvh.

Abstract To estimate appearance parameters, traditional SVBRDF acquisition methods require multiple input images to be captured with various angles of light and camera, followed by a post‐processing step. For this reason, subjects have been limited to static scenes, or a multiview system is required to capture dynamic objects. In this paper, we propose a simultaneous acquisition method of SVBRDF and shape allowing us to capture the material appearance of deformable objects in motion using a single RGBD camera. To do so, we progressively integrate photometric samples of surfaces in motion in a volumetric data structure with a deformation graph. Then, building upon recent advances of fusion‐based methods, we estimate SVBRDF parameters in motion. We make use of a conventional RGBD camera that consists of the colour and infrared cameras with active infrared illumination. The colour camera is used for capturing diffuse properties, and the infrared camera‐illumination module is employed for estimating specular properties by means of active illumination. Our joint optimization yields complete material appearance parameters. We demonstrate the effectiveness of our method with extensive evaluation on both synthetic and real data that include various deformable objects of specular and diffuse appearance.

Hair is one of the most challenging objects to reconstruct due to its micro-scale structure and a large number of repeated strands with heavy occlusions. In this paper, we present the first method to capture high-fidelity hair geometry with strand-level accuracy. Our method takes three stages to achieve this. In the first stage, a new multi-view stereo method with a slanted support line is proposed to solve the hair correspondences between different views. In detail, we contribute a novel cost function consisting of both photo-consistency term and geometric term that reconstructs each hair pixel as a 3D line. By merging all the depth maps, a point cloud, as well as local line directions for each point, is obtained. Thus, in the second stage, we feature a novel strand reconstruction method with the mean-shift to convert the noisy point data to a set of strands. Lastly, we grow the hair strands with multi-view geometric constraints to elongate the short strands and recover the missing strands, thus significantly increasing the reconstruction completeness. We evaluate our method on both synthetic data and real captured data, showing that our method can reconstruct hair strands with sub-millimeter accuracy.

Capturing spatially-varying bidirectional reflectance distribution functions (SVBRDFs) of 3D objects with just a single, hand-held camera (such as an off-the-shelf smartphone or a DSLR camera) is a difficult, open problem. Previous works are either limited to planar geometry, or rely on previously scanned 3D geometry, thus limiting their practicality. There are several technical challenges that need to be overcome: First, the built-in flash of a camera is almost colocated with the lens, and at a fixed position; this severely hampers sampling procedures in the light-view space. Moreover, the near-field flash lights the object partially and unevenly. In terms of geometry, existing multiview stereo techniques assume diffuse reflectance only, which leads to overly smoothed 3D reconstructions, as we show in this paper. We present a simple yet powerful framework that removes the need for expensive, dedicated hardware, enabling practical acquisition of SVBRDF information from real-world, 3D objects with a single, off-the-shelf camera with a built-in flash. In addition, by removing the diffuse reflection assumption and leveraging instead such SVBRDF information, our method outputs high-quality 3D geometry reconstructions, including more accurate high-frequency details than state-of-the-art multiview stereo techniques. We formulate the joint reconstruction of SVBRDFs, shading normals, and 3D geometry as a multi-stage, iterative inverse-rendering reconstruction pipeline. Our method is also directly applicable to any existing multiview 3D reconstruction technique. We present results of captured objects with complex geometry and reflectance; we also validate our method numerically against other existing approaches that rely on dedicated hardware, additional sources of information, or both.

We present a novel hyperspectral image reconstruction algorithm, which overcomes the long-standing tradeoff between spectral accuracy and spatial resolution in existing compressive imaging approaches. Our method consists of two steps: First, we learn nonlinear spectral representations from real-world hyperspectral datasets; for this, we build a convolutional autoencoder which allows reconstructing its own input through its encoder and decoder networks. Second, we introduce a novel optimization method, which jointly regularizes the fidelity of the learned nonlinear spectral representations and the sparsity of gradients in the spatial domain, by means of our new fidelity prior. Our technique can be applied to any existing compressive imaging architecture, and has been thoroughly tested both in simulation, and by building a prototype hyperspectral imaging system. It outperforms the state-of-the-art methods from each architecture, both in terms of spectral accuracy and spatial resolution, while its computational complexity is reduced by two orders of magnitude with respect to sparse coding techniques. Moreover, we present two additional applications of our method: hyperspectral interpolation and demosaicing. Last, we have created a new high-resolution hyperspectral dataset containing sharper images of more spectral variety than existing ones, available through our project website.

Acquiring microscale reflectance and normals is useful for digital documentation and identification of real-world materials. However, its simultaneous acquisition has rarely been explored due to the difficulties of combining both sources of information at such small scale. In this paper, we capture both spatially-varying material appearance (diffuse, specular and roughness) and normals simultaneously at the microscale resolution. We design and build a microscopic light dome with 374 LED lights over the hemisphere, specifically tailored to the characteristics of microscopic imaging. This allows us to achieve the highest resolution for such combined information among current state-of-the-art acquisition systems. We thoroughly test and characterize our system, and provide microscopic appearance measurements of a wide range of common materials, as well as renderings of novel views to validate the applicability of our captured data. Additional applications such as bi-scale material editing from real-world samples are also demonstrated.