Related papers: SVRecon: Sparse Voxel Rasterization for Surface Re…

Neural implicit surface reconstruction with signed distance function has made significant progress, but recovering fine details such as thin structures and complex geometries remains challenging due to unreliable or noisy geometric priors.…

In this paper, we develop a new method, termed SDF-3DGAN, for 3D object generation and 3D-Aware image synthesis tasks, which introduce implicit Signed Distance Function (SDF) as the 3D object representation method in the generative field.…

Geometric reconstruction of opaque surfaces from images is a longstanding challenge in computer vision, with renewed interest from volumetric view synthesis algorithms using radiance fields. We leverage the geometry field proposed in recent…

Scene and object reconstruction is an important problem in robotics, in particular in planning collision-free trajectories or in object manipulation. This paper compares two strategies for the reconstruction of nonvisible parts of the…

3D Gaussian Splatting (3DGS) has emerged as a promising approach for 3D scene representation, offering a reduction in computational overhead compared to Neural Radiance Fields (NeRF). However, 3DGS is susceptible to high-frequency artifacts…

LiDAR-based fully sparse architecture has garnered increasing attention. FSDv1 stands out as a representative work, achieving impressive efficacy and efficiency, albeit with intricate structures and handcrafted designs. In this paper, we…

Sparse-voxel rasterization is a fast, differentiable alternative for optimization-based scene reconstruction, but it tends to underfit low-frequency content, depends on brittle pruning heuristics, and can overgrow in ways that inflate VRAM.…

We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction. Given a stream of posed depth images from a moving camera, it trains a randomly initialised neural network to map input 3D coordinate to…

We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground…

We present a novel deep learning-based approach to the 3D reconstruction of clothed humans using weak supervision via 2D normal maps. Given a single RGB image or multiview images, our network infers a signed distance function (SDF)…

We investigate the reconstruction problem of limited angle tomography. Such problems arise naturally in applications like digital breast tomosynthesis, dental tomography, electron microscopy etc. Since the acquired tomographic data is…

We present a StyleGAN2-based deep learning approach for 3D shape generation, called SDF-StyleGAN, with the aim of reducing visual and geometric dissimilarity between generated shapes and a shape collection. We extend StyleGAN2 to 3D…

To achieve fully autonomous navigation, vehicles need to compute an accurate model of their direct surrounding. In this paper, a 3D surface reconstruction algorithm from heterogeneous density 3D data is presented. The proposed method is…

The generation of high-fidelity view synthesis is essential for robotic navigation and interaction but remains challenging, particularly in indoor environments and real-time scenarios. Existing techniques often require significant…

Neural Surface Reconstruction has become a standard methodology for indoor 3D reconstruction, with Signed Distance Functions (SDFs) proving particularly effective for representing scene geometry. A variety of applications require a detailed…

This paper proposes a deep-learning-based method for recovering a signed distance function (SDF) of a given hypersurface represented by an implicit level set function. Using the flexibility of constructing a neural network, we use an…

Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering. However, existing methods based on signed distance function (SDF) are limited to closed surfaces, failing…

We present a method to automatically compute correct gradients with respect to geometric scene parameters in neural SDF renderers. Recent physically-based differentiable rendering techniques for meshes have used edge-sampling to handle…

The 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi-view images, enabling real-time rendering. While point-based rasterization effectively reduces computational demands for…

Recent learning-based Multi-View Stereo models have demonstrated state-of-the-art performance in sparse-view 3D reconstruction. However, directly applying 3D Gaussian Splatting (3DGS) as a refinement step following these models presents…