Related papers: ROAR: Robust Adaptive Reconstruction of Shapes Usi…
With the recent advances in hardware and rendering techniques, 3D models have emerged everywhere in our life. Yet creating 3D shapes is arduous and requires significant professional knowledge. Meanwhile, Deep learning has enabled…
We present a topology-informed inverse rendering approach for reconstructing high-genus surface meshes from multi-view images. Compared to 3D representations like voxels and point clouds, mesh-based representations are preferred as they…
Modeling 3D articulated objects with realistic geometry, textures, and kinematics is essential for a wide range of applications. However, existing optimization-based reconstruction methods often require dense multi-view inputs and expensive…
Industrial 3D face assets creation typically reconstructs topology-consistent face meshes from multi-view images for downstream production. However, high-quality reconstruction usually requires manual processing or specific capture…
A key challenge in the task of human pose and shape estimation is occlusion, including self-occlusions, object-human occlusions, and inter-person occlusions. The lack of diverse and accurate pose and shape training data becomes a major…
Simultaneously odometry and mapping using LiDAR data is an important task for mobile systems to achieve full autonomy in large-scale environments. However, most existing LiDAR-based methods prioritize tracking quality over reconstruction…
Creating high-fidelity 3D meshes with arbitrary topology, including open surfaces and complex interiors, remains a significant challenge. Existing implicit field methods often require costly and detail-degrading watertight conversion, while…
Sparse-view 3D reconstruction is essential for applications in which dense image acquisition is impractical, such as robotics, augmented/virtual reality (AR/VR), and autonomous systems. In these settings, minimal image overlap prevents…
We present Hierarchical Motion Representation (HiMoR), a novel deformation representation for 3D Gaussian primitives capable of achieving high-quality monocular dynamic 3D reconstruction. The insight behind HiMoR is that motions in everyday…
3D image reconstruction from a limited number of 2D images has been a long-standing challenge in computer vision and image analysis. While deep learning-based approaches have achieved impressive performance in this area, existing deep…
Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate camera poses as input, which could be difficult to obtain in…
Reconstructing 3D human shape and pose from monocular images is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from…
We propose DiMeR, a novel geometry-texture disentangled feed-forward model with 3D supervision for sparse-view mesh reconstruction. Existing methods confront two persistent obstacles: (i) textures can conceal geometric errors, i.e.,…
Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong scene priors from massive RGB datasets. However, their effectiveness drops when applied to…
Regression-based LiDAR relocalization has recently emerged as a promising solution for high-precision positioning in GNSS-denied environments. However, these methods are primarily tailored to autonomous driving, exhibiting significantly…
Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in image-based 3D reconstruction. However, their implicit volumetric representations differ significantly from the widely-adopted polygonal meshes and lack support…
Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics - a triangular mesh -…
Current 3D representations like meshes, voxels, point clouds, and NeRF-based neural implicit fields exhibit significant limitations: they are often task-specific, lacking universal applicability across reconstruction, generation, editing,…
Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive no explicit guidance about which cross-part interactions should drive the motion. We…
This paper addresses the limitations of neural rendering-based multi-view surface reconstruction methods, which require an additional mesh extraction step that is inconvenient and would produce poor-quality surfaces with mesh aliasing,…