Related papers: Point3R: Streaming 3D Reconstruction with Explicit…

Recent feed-forward geometry foundation models have demonstrated impressive generalization by recovering depth and poses in a single forward pass. However, these models are typically constrained by a global coordinate frame assumption. This…

In this paper, a method for dense semantic 3D scene reconstruction from an RGB-D sequence is proposed to solve high-level scene understanding tasks. First, each RGB-D pair is consistently segmented into 2D semantic maps based on a camera…

3D dense reconstruction refers to the process of obtaining the complete shape and texture features of 3D objects from 2D planar images. 3D reconstruction is an important and extensively studied problem, but it is far from being solved. This…

We present a real-time monocular dense SLAM system designed bottom-up from MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system is robust on in-the-wild video sequences despite making no…

Building a robust perception module is crucial for visuomotor policy learning. While recent methods incorporate pre-trained 2D foundation models into robotic perception modules to leverage their strong semantic understanding, they struggle…

Generation of 3D data by deep neural network has been attracting increasing attention in the research community. The majority of extant works resort to regular representations such as volumetric grids or collection of images; however, these…

Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for…

Volumetric neural rendering methods like NeRF generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time. On the other hand, deep multi-view stereo methods can quickly reconstruct…

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions,…

We introduce G-CUT3R, a novel feed-forward approach for guided 3D scene reconstruction that enhances the CUT3R model by integrating prior information. Unlike existing feed-forward methods that rely solely on input images, our method…

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

Implicit neural 3D representation has achieved impressive results in surface or scene reconstruction and novel view synthesis, which typically uses the coordinate-based multi-layer perceptrons (MLPs) to learn a continuous scene…

A successful point cloud registration often lies on robust establishment of sparse matches through discriminative 3D local features. Despite the fast evolution of learning-based 3D feature descriptors, little attention has been drawn to the…

Reconstructing scenes and tracking motion are two sides of the same coin. Tracking points allow for geometric reconstruction [14], while geometric reconstruction of (dynamic) scenes allows for 3D tracking of points over time [24, 39]. The…

3D super-resolution (3DSR) aims to reconstruct high-resolution (HR) 3D scenes from low-resolution (LR) multi-view images. Existing methods rely on dense LR inputs and per-scene optimization, which restricts the high-frequency priors for…

This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds. Despite the recent success achieved by extending deep implicit representations into 4D space, it is still a great challenge in two respects, i.e. how…

3D spatial perception is fundamental to generalizable robotic manipulation, yet obtaining reliable, high-quality 3D geometry remains challenging. Depth sensors suffer from noise and material sensitivity, while existing reconstruction models…

LiDAR-produced point clouds are the major source for most state-of-the-art 3D object detectors. Yet, small, distant, and incomplete objects with sparse or few points are often hard to detect. We present Sparse2Dense, a new framework to…

In recent years, implicit functions have drawn attention in the field of 3D reconstruction and have successfully been applied with Deep Learning. However, for incremental reconstruction, implicit function-based registrations have been…

Multi-view 3D reconstruction remains a core challenge in computer vision. Recent methods, such as DUST3R and its successors, directly regress pointmaps from image pairs without relying on known scene geometry or camera parameters. However,…