Existing Gaussian avatar methods typically parameterize geometry on a body-template surface, which entangles the avatar's representation space with the template's deformation space and limits the capture of layered, off-body, and non-rigid clothing geometry. We present PiG-Avatar, which addresses this limitation by using the parametric body model solely for kinematic transport, while representing the avatar as Gaussians anchored in a volumetric canonical space governed by a continuous neural field. This decouples representation from template topology, avoiding the geometric constraints of surface-based parameterizations. Kinematic coherence is maintained through 3D barycentric anchor transport, which guides motion without constraining geometry and allows anchors to deviate freely from the template surface, yielding dense, stable temporal surface correspondences by construction. To make this unconstrained formulation tractable, we introduce dual-level spatially coherent optimization, combining Sobolev-preconditioned neural-field updates with a novel KNN-based preconditioning of canonical anchor geometry. Together, these mechanisms induce an emergent self-organization of anchor density: anchors migrate toward regions of high curvature, appearance variation, and non-coherent motion without explicit heuristics. As a result, complex clothing geometry and layered surfaces emerge as natural, high-fidelity outputs. This single representation further supports hierarchical reconstruction across multiple levels of detail, with coarse-level supervision propagating to finer levels through the shared field and coupled anchor graph. On established benchmarks featuring subjects with complex clothing and challenging non-rigid motion, PiG-Avatar achieves state-of-the-art rendering quality, generalizes robustly to imperfect body model initialization, and renders in real time across all detail levels.

emporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. Existing methods either optimize deformations incrementally, risking drift and requiring long runtimes, or rely on complex learned models that demand category-specific training. We present Neu-PiG, a fast optimization method based on a novel preconditioned surface encoding that estimates coherent non-rigid deformations without sacrificing temporal stability or accuracy. Our method encodes entire deformations across all time steps at various spatial scales into a multi-resolution latent grid, parameterized by the position and normal direction of a reference surface from a single keyframe. This latent representation is then augmented for time modulation and decoded into per-frame 6-DoF deformations via a lightweight multi-layer perceptron (MLP). To achieve high-fidelity, drift-free surface reconstructions in seconds, we employ Sobolev preconditioning during gradient-based training of the latent space, completely avoiding the need for any explicit correspondences or further priors. Experiments across diverse human and animal datasets demonstrate that Neu-PiG outperforms state-the-art approaches, offering both superior accuracy and scalability to long sequences while running at least 60× faster than existing training-free methods and even matching the inference-time performance of heavy pretrained models.

Reconstructing an object's shape and appearance in terms of a mesh textured by a spatially-varying bidirectional reflectance distribution function (SVBRDF) from a limited set of images captured under collocated light is an ill-posed problem. Previous state-of-the-art approaches either aim to reconstruct the appearance directly on the geometry or additionally use texture normals as part of the appearance features. However, this requires detailed but inefficiently large meshes, that would have to be simplified in a post-processing step, or suffers from well-known limitations of normal maps such as missing shadows or incorrect silhouettes. Another limiting factor is the fixed and typically low resolution of the texture estimation resulting in loss of important surface details. To overcome these problems, we present ROSA, an inverse rendering method that directly optimizes mesh geometry with spatially adaptive mesh resolution solely based on the image data. In particular, we refine the mesh and locally condition the surface smoothness based on the estimated normal texture and mesh curvature. In addition, we enable the reconstruction of fine appearance details in high-resolution textures through a pioneering tile-based method that operates on a single pre-trained decoder network but is not limited by the network output resolution.

Dynamic surface reconstruction of objects from point cloud sequences is a challenging field in computer graphics. Existing approaches either require multiple regularization terms or extensive training data which, however, lead to compromises in reconstruction accuracy as well as over-smoothing or poor generalization to unseen objects and motions. To address these lim- itations, we introduce Preconditioned Deformation Grids, a novel technique for estimating coherent deformation fields directly from unstructured point cloud sequences without requiring or forming explicit correspondences. Key to our approach is the use of multi-resolution voxel grids that capture the overall motion at varying spatial scales, enabling a more flexible deformation representation. In conjunction with incorporating grid-based Sobolev preconditioning into gradient-based optimization, we show that applying a Chamfer loss between the input point clouds as well as to an evolving template mesh is sufficient to obtain accurate deformations. To ensure temporal consistency along the object surface, we include a weak isometry loss on mesh edges which complements the main objective without constraining deformation fidelity. Extensive evaluations demonstrate that our method achieves superior results, particularly for long sequences, compared to state-of-the-art techniques.

In this paper, we present an inverse rendering method for the simple reconstruction of shape and appearance of real-world objects from only roughly calibrated RGB images captured under collocated point light illumination. To this end, we gradually reconstruct the lower-frequency geometry information using automatically generated occupancy mask images based on a visual hull initialization of the mesh, to infer the object topology, and a smoothness-preconditioned optimization. By combining this geometry estimation with learning-based SVBRDF parameter inference as well as intrinsic and extrinsic camera parameter refinement in a joint and unified formulation, our novel method is able to reconstruct shape and an isotropic SVBRDF from fewer input images than previous methods. Unlike in other works, we also estimate normal maps as part of the SVBRDF to capture and represent higher-frequency geometric details in a compact way. Furthermore, by regularizing the appearance estimation with a GAN-based SVBRDF generator, we are able to meaningfully limit the solution space. In summary, this leads to a robust automatic reconstruction algorithm for shape and appearance. We evaluated our algorithm on synthetic as well as on real-world data and demonstrate that our method is able to reconstruct complex objects with high-fidelity reflection properties in a robust way, also in the presence of imperfect camera parameter data.

In this paper, we present an inverse rendering method for the simple reconstruction of shape and appearance of real-world objects from only roughly calibrated RGB-images captured under collocated point-light illumination.To this end, we gradually reconstruct the lower-frequency geometry information using automatically generated occupancy mask images based on a visual hull initialization of the mesh, to infer the object topology, and a smoothness-preconditioned optimization.By combining this geometry estimation with learning-based SVBRDF parameter inference as well as intrinsic and extrinsic camera parameter refinement in a joint and unified formulation, our novel method is able to reconstruct shape and an isotropic SVBRDF from fewer input images than previous methods.Unlike in other works, we also estimate normal maps as part of the SVBRDF to capture and represent higher-frequency geometric details in a compact way.Furthermore, by regularizing the appearance estimation with a GAN-based SVBRDF generator, we are able to meaningfully limit the solution space.

Noise-like artifacts are common in measured or fitted data across various domains, e.g. photography, geometric reconstructions in terms of point clouds or meshes, as well as reflectance measurements and the respective fitting of commonly used reflectance models to them. State-of-the-art denoising approaches focus on specific noise characteristics usually observed in photography. However, these approaches do not perform well if data is corrupted with location-dependent noise. A typical example is the acquisition of heterogeneous materials, which leads to different noise levels due to different behavior of the components either during acquisition or during reconstruction. We address this problem by first automatically determining location-dependent noise levels in the input data and demonstrate that state-of-the-art denoising algorithms can usually benefit from this guidance with only minor modifications to their loss function or employed regularization mechanisms. To generate this information for guidance, we analyze patchwise variances and subsequently derive per-pixel importance values. We demonstrate the benefits of such locally-guided denoising at the examples of the Deep Image Prior method and the Self2Self method.

In this work, we adapt and improve recent isotropic material estimation efforts to estimate spatially varying anisotropic materials with an additional Fresnel term using a variable set of input images and are able to handle any resolution. We combine an initial estimation network with an auto-encoder to fine-tune the decoding of latent embedded appearance parameters on the input images to produce finely detailed SVBRDFs. For this purpose, the training must be adapted so that the determination is possible on the basis of a small number of images that still capture as much reflective behavior of materials as possible. The resulting appearance parameters are capable of capturing and reconstructing complex spatially varying features in detail, but place increased demands on the input images.