Related papers: GLVD: Guided Learned Vertex Descent

Neural implicit functions have brought impressive advances to the state-of-the-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen…

We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, most existing approaches…

In this paper, we address the problem of reconstructing an object's surface from a single image using generative networks. First, we represent a 3D surface with an aggregation of dense point clouds from multiple views. Each point cloud is…

In this work, we present Fed3DGS, a scalable 3D reconstruction framework based on 3D Gaussian splatting (3DGS) with federated learning. Existing city-scale reconstruction methods typically adopt a centralized approach, which gathers all…

Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end training or map features to compressed representations, discarding the dense spatial…

In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo…

Over the past few years, single-view 3D face reconstruction methods can produce beautiful 3D models. Nevertheless,the input of these works is unobstructed faces.We describe a system designed to reconstruct convincing face texture in the…

3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D reconstruction using convolutional neural…

Existing 3D reconstruction methods utilize guidances such as 2D images, 3D point clouds, shape contours and single semantics to recover the 3D surface, which limits the creative exploration of 3D modeling. In this paper, we propose a novel…

We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a "foundation" model for monocular depth estimation and…

Recent learning-based approaches, in which models are trained by single-view images have shown promising results for monocular 3D face reconstruction, but they suffer from the ill-posed face pose and depth ambiguity issue. In contrast to…

Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an…

Neural reconstruction models for autonomous driving simulation have made significant strides in recent years, with dynamic models becoming increasingly prevalent. However, these models are typically limited to handling in-domain objects…

Feed-forward 3D reconstruction has revolutionized 3D vision, providing a powerful baseline for downstream tasks such as novel-view synthesis with 3D Gaussian Splatting. Previous works explore fixing the corrupted rendering results with a…

We present a novel method to improve the accuracy of the 3D reconstruction of clothed human shape from a single image. Recent work has introduced volumetric, implicit and model-based shape learning frameworks for reconstruction of objects…

Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have advanced 3D reconstruction and novel view synthesis, but remain heavily dependent on accurate camera poses and dense viewpoint coverage. These requirements limit their…

We present Gradient-SDF, a novel representation for 3D geometry that combines the advantages of implict and explicit representations. By storing at every voxel both the signed distance field as well as its gradient vector field, we enhance…

We are witnessing an explosion of neural implicit representations in computer vision and graphics. Their applicability has recently expanded beyond tasks such as shape generation and image-based rendering to the fundamental problem of…

Deep learning based 3D shape generation methods generally utilize latent features extracted from color images to encode the semantics of objects and guide the shape generation process. These color image semantics only implicitly encode 3D…

We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE). Unlike the…