Scalable and High-Quality Neural Implicit Representation for 3D Reconstruction

Various SDF-based neural implicit surface reconstruction methods have been proposed recently, and have demonstrated remarkable modeling capabilities. However, due to the global nature and limited representation ability of a single network, existing methods still suffer from many drawbacks, such as limited accuracy and scale of the reconstruction. In this paper, we propose a versatile, scalable and high-quality neural implicit representation to address these issues. We integrate a divide-and-conquer approach into the neural SDF-based reconstruction. Specifically, we model the object or scene as a fusion of multiple independent local neural SDFs with overlapping regions. The construction of our representation involves three key steps: (1) constructing the distribution and overlap relationship of the local radiance fields based on object structure or data distribution, (2) relative pose registration for adjacent local SDFs, and (3) SDF blending. Thanks to the independent representation of each local region, our approach can not only achieve high-fidelity surface reconstruction, but also enable scalable scene reconstruction. Extensive experimental results demonstrate the effectiveness and practicality of our proposed method.

Matching Free Depth Recovery from Structured Light

We present a novel approach for depth estimation from images captured by structured light systems. Unlike many previous methods that rely on image matching process, our approach uses a density voxel grid to represent scene geometry, which is trained via self-supervised differentiable volume rendering. Our method leverages color fields derived from projected patterns in structured light systems during the rendering process, enabling the isolated optimization of the geometry field. This contributes to faster convergence and high-quality output. Additionally, we incorporate normalized device coordinates (NDC), a distortion loss, and a novel surface-based color loss to enhance geometric fidelity. Experimental results demonstrate that our method outperforms existing matching-based techniques in geometric performance for few-shot scenarios, achieving approximately a 60% reduction in average estimated depth errors on synthetic scenes and about 30% on real-world captured scenes. Furthermore, our approach delivers fast training, with a speed roughly three times faster than previous matching-free methods that employ implicit representations.

D$^3$-Human: Dynamic Disentangled Digital Human from Monocular Video

We introduce D$^3$-Human, a method for reconstructing Dynamic Disentangled Digital Human geometry from monocular videos. Past monocular video human reconstruction primarily focuses on reconstructing undecoupled clothed human bodies or only reconstructing clothing, making it difficult to apply directly in applications such as animation production. The challenge in reconstructing decoupled clothing and body lies in the occlusion caused by clothing over the body. To this end, the details of the visible area and the plausibility of the invisible area must be ensured during the reconstruction process. Our proposed method combines explicit and implicit representations to model the decoupled clothed human body, leveraging the robustness of explicit representations and the flexibility of implicit representations. Specifically, we reconstruct the visible region as SDF and propose a novel human manifold signed distance field (hmSDF) to segment the visible clothing and visible body, and then merge the visible and invisible body. Extensive experimental results demonstrate that, compared with existing reconstruction schemes, D$^3$-Human can achieve high-quality decoupled reconstruction of the human body wearing different clothing, and can be directly applied to clothing transfer and animation.

SparseLGS: Sparse View Language Embedded Gaussian Splatting

Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods perform well, they essentially require very dense multi-view inputs, limiting their applicability in real-world scenarios. In this work, we propose SparseLGS to address the challenge of 3D scene understanding with pose-free and sparse view input images. Our method leverages a learning-based dense stereo model to handle pose-free and sparse inputs, and a three-step region matching approach to address the multi-view semantic inconsistency problem, which is especially important for sparse inputs. Different from directly learning high-dimensional CLIP features, we extract low-dimensional information and build bijections to avoid excessive learning and storage costs. We introduce a reconstruction loss during semantic training to improve Gaussian positions and shapes. To the best of our knowledge, we are the first to address the 3D semantic field problem with sparse pose-free inputs. Experimental results show that SparseLGS achieves comparable quality when reconstructing semantic fields with fewer inputs (3-4 views) compared to previous SOTA methods with dense input. Besides, when using the same sparse input, SparseLGS leads significantly in quality and heavily improves the computation speed (5$\times$ speedup). Project page: {\tt\small \url{https://ustc3dv.github.io/SparseLGS}}

One Shot, One Talk: Whole-body Talking Avatar from a Single Image

Building realistic and animatable avatars still requires minutes of multi-view or monocular self-rotating videos, and most methods lack precise control over gestures and expressions. To push this boundary, we address the challenge of constructing a whole-body talking avatar from a single image. We propose a novel pipeline that tackles two critical issues: 1) complex dynamic modeling and 2) generalization to novel gestures and expressions. To achieve seamless generalization, we leverage recent pose-guided image-to-video diffusion models to generate imperfect video frames as pseudo-labels. To overcome the dynamic modeling challenge posed by inconsistent and noisy pseudo-videos, we introduce a tightly coupled 3DGS-mesh hybrid avatar representation and apply several key regularizations to mitigate inconsistencies caused by imperfect labels. Extensive experiments on diverse subjects demonstrate that our method enables the creation of a photorealistic, precisely animatable, and expressive whole-body talking avatar from just a single image.

Deformable NeRF using Recursively Subdivided Tetrahedra

While neural radiance fields (NeRF) have shown promise in novel view synthesis, their implicit representation limits explicit control over object manipulation. Existing research has proposed the integration of explicit geometric proxies to enable deformation. However, these methods face two primary challenges: firstly, the time-consuming and computationally demanding tetrahedralization process; and secondly, handling complex or thin structures often leads to either excessive, storage-intensive tetrahedral meshes or poor-quality ones that impair deformation capabilities. To address these challenges, we propose DeformRF, a method that seamlessly integrates the manipulability of tetrahedral meshes with the high-quality rendering capabilities of feature grid representations. To avoid ill-shaped tetrahedra and tetrahedralization for each object, we propose a two-stage training strategy. Starting with an almost-regular tetrahedral grid, our model initially retains key tetrahedra surrounding the object and subsequently refines object details using finer-granularity mesh in the second stage. We also present the concept of recursively subdivided tetrahedra to create higher-resolution meshes implicitly. This enables multi-resolution encoding while only necessitating the storage of the coarse tetrahedral mesh generated in the first training stage. We conduct a comprehensive evaluation of our DeformRF on both synthetic and real-captured datasets. Both quantitative and qualitative results demonstrate the effectiveness of our method for novel view synthesis and deformation tasks. Project page: https://ustc3dv.github.io/DeformRF/

End-to-end Surface Optimization for Light Control

Designing a freeform surface to reflect or refract light to achieve a target distribution is a challenging inverse problem. In this paper, we propose an end-to-end optimization strategy for an optical surface mesh. Our formulation leverages a novel differentiable rendering model, and is directly driven by the difference between the resulting light distribution and the target distribution. We also enforce geometric constraints related to fabrication requirements, to facilitate CNC milling and polishing of the designed surface. To address the issue of local minima, we formulate a face-based optimal transport problem between the current mesh and the target distribution, which makes effective large changes to the surface shape. The combination of our optimal transport update and rendering-guided optimization produces an optical surface design with a resulting image closely resembling the target, while the fabrication constraints in our optimization help to ensure consistency between the rendering model and the final physical results. The effectiveness of our algorithm is demonstrated on a variety of target images using both simulated rendering and physical prototypes.

Semantic Communications for 3D Human Face Transmission with Neural Radiance Fields

This paper investigates the transmission of three-dimensional (3D) human face content for immersive communication over a rate-constrained transmitter-receiver link. We propose a new framework named NeRF-SeCom, which leverages neural radiance fields (NeRF) and semantic communications to improve the quality of 3D visualizations while minimizing the communication overhead. In the NeRF-SeCom framework, we first train a NeRF face model based on the NeRFBlendShape method, which is pre-shared between the transmitter and receiver as the semantic knowledge base to facilitate the real-time transmission. Next, with knowledge base, the transmitter extracts and sends only the essential semantic features for the receiver to reconstruct 3D face in real time. To optimize the transmission efficiency, we classify the expression features into static and dynamic types. Over each video chunk, static features are transmitted once for all frames, whereas dynamic features are transmitted over a portion of frames to adhere to rate constraints. Additionally, we propose a feature prediction mechanism, which allows the receiver to predict the dynamic features for frames that are not transmitted. Experiments show that our proposed NeRF-SeCom framework significantly outperforms benchmark methods in delivering high-quality 3D visualizations of human faces.

PICA: Physics-Integrated Clothed Avatar

We introduce PICA, a novel representation for high-fidelity animatable clothed human avatars with physics-accurate dynamics, even for loose clothing. Previous neural rendering-based representations of animatable clothed humans typically employ a single model to represent both the clothing and the underlying body. While efficient, these approaches often fail to accurately represent complex garment dynamics, leading to incorrect deformations and noticeable rendering artifacts, especially for sliding or loose garments. Furthermore, previous works represent garment dynamics as pose-dependent deformations and facilitate novel pose animations in a data-driven manner. This often results in outcomes that do not faithfully represent the mechanics of motion and are prone to generating artifacts in out-of-distribution poses. To address these issues, we adopt two individual 3D Gaussian Splatting (3DGS) models with different deformation characteristics, modeling the human body and clothing separately. This distinction allows for better handling of their respective motion characteristics. With this representation, we integrate a graph neural network (GNN)-based clothed body physics simulation module to ensure an accurate representation of clothing dynamics. Our method, through its carefully designed features, achieves high-fidelity rendering of clothed human bodies in complex and novel driving poses, significantly outperforming previous methods under the same settings.

SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid Registration

Existing optimization-based methods for non-rigid registration typically minimize an alignment error metric based on the point-to-point or point-to-plane distance between corresponding point pairs on the source surface and target surface. However, these metrics can result in slow convergence or a loss of detail. In this paper, we propose SPARE, a novel formulation that utilizes a symmetrized point-to-plane distance for robust non-rigid registration. The symmetrized point-to-plane distance relies on both the positions and normals of the corresponding points, resulting in a more accurate approximation of the underlying geometry and can achieve higher accuracy than existing methods. To solve this optimization problem efficiently, we propose an alternating minimization solver using a majorization-minimization strategy. Moreover, for effective initialization of the solver, we incorporate a deformation graph-based coarse alignment that improves registration quality and efficiency. Extensive experiments show that the proposed method greatly improves the accuracy of non-rigid registration problems and maintains relatively high solution efficiency. The code is publicly available at https://github.com/yaoyx689/spare.