Related papers: Preconditioned Deformation Grids
If robots could reliably manipulate the shape of 3D deformable objects, they could find applications in fields ranging from home care to warehouse fulfillment to surgical assistance. Analytic models of elastic, 3D deformable objects require…
Neural signed distance functions (SDFs) have shown powerful ability in fitting the shape geometry. However, inferring continuous signed distance fields from discrete unoriented point clouds still remains a challenge. The neural network…
Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task, particularly with real-world data. Current state-of-the-art methods develop Transformer-based implicit field learning, necessitating an…
Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR models are trained specifically for one scene. If training…
Dense point cloud generation from a sparse or incomplete point cloud is a crucial and challenging problem in 3D computer vision and computer graphics. So far, the existing methods are either computationally too expensive, suffer from…
3D world models (i.e., learning-based 3D dynamics models) offer a promising approach to generalizable robotic manipulation by capturing the underlying physics of environment evolution conditioned on robot actions. However, existing 3D world…
Scene graphs have emerged as accurate descriptive priors for image generation and manipulation tasks, however, their complexity and diversity of the shapes and relations of objects in data make it challenging to incorporate them into the…
Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which…
Surface reconstruction is a fundamental problem in 3D graphics. In this paper, we propose a learning-based approach for implicit surface reconstruction from raw point clouds without normals. Our method is inspired by Gauss Lemma in…
Learning object-centric representations from unsupervised videos is challenging. Unlike most previous approaches that focus on decomposing 2D images, we present a 3D generative model named DynaVol-S for dynamic scenes that enables…
In this work, we explore the idea that effective generative models for point clouds under the autoencoding framework must acknowledge the relationship between a continuous surface, a discretized mesh, and a set of points sampled from the…
Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextual relationships between distant objects presents additional…
This paper proposes a novel controllable human motion synthesis method for fine-level deformation based on static point-based radiance fields. Although previous editable neural radiance field methods can generate impressive results on…
We challenge the common assumption that deeper decoder architectures always yield better performance in point cloud reconstruction. Our analysis reveals that, beyond a certain depth, increasing decoder complexity leads to overfitting and…
This paper presents a learning-based, lossless compression method for static point cloud geometry, based on context-adaptive arithmetic coding. Unlike most existing methods working in the octree domain, our encoder operates in a hybrid…
Point-cloud data collected in real-world applications are often incomplete. Data is typically missing due to objects being observed from partial viewpoints, which only capture a specific perspective or angle. Additionally, data can be…
We present an efficient and automatic approach for accurate reconstruction of instances of big 3D objects from multiple, unorganized and unstructured point clouds, in presence of dynamic clutter and occlusions. In contrast to conventional…
In the field of 3D scene understanding, 3D scene graphs have emerged as a new scene representation that combines geometric and semantic information about objects and their relationships. However, learning semantic 3D scene graphs in a fully…
Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector.…
High-quality point cloud data is a critical foundation for tasks such as autonomous driving and 3D reconstruction. However, LiDAR-based point cloud acquisition is often affected by various disturbances, resulting in a large number of noise…