Related papers: Robo3R: Enhancing Robotic Manipulation with Accura…
Precise robot manipulations require rich spatial information in imitation learning. Image-based policies model object positions from fixed cameras, which are sensitive to camera view changes. Policies utilizing 3D point clouds usually…
Perceiving accurate 3D object shape is important for robots to interact with the physical world. Current research along this direction has been primarily relying on visual observations. Vision, however useful, has inherent limitations due…
Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel Gaussians and combine Gaussians from all views as the scene…
We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to…
Dense 3D scene reconstruction from an ordered sequence or unordered image collections is a critical step when bringing research in computer vision into practical scenarios. Following the paradigm introduced by DUSt3R, which unifies an image…
Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical world. While traditional methods achieve high fidelity,…
In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DUSt3R, that are originally designed for static 3D scene…
We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses…
Many works in collaborative robotics and human-robot interaction focuses on identifying and predicting human behaviour while considering the information about the robot itself as given. This can be the case when sensors and the robot are…
We introduce a new task, Map and Locate, which unifies the traditionally distinct objectives of open-vocabulary segmentation - detecting and segmenting object instances based on natural language queries - and 3D reconstruction, the process…
The rapid development of Large Multimodal Models (LMMs) has led to remarkable progress in 2D visual understanding; however, extending these capabilities to 3D scene understanding remains a significant challenge. Existing approaches…
Dense matching methods like DUSt3R regress pairwise pointmaps for 3D reconstruction. However, the reliance on pairwise prediction and the limited generalization capability inherently restrict the global geometric consistency. In this work,…
Robotic ultrasound (US) imaging has been seen as a promising solution to overcome the limitations of free-hand US examinations, i.e., inter-operator variability. However, the fact that robotic US systems cannot react to subject movements…
The application of monocular dense Simultaneous Localization and Mapping (SLAM) is often hindered by high latency, large GPU memory consumption, and reliance on camera calibration. To relax this constraint, we propose EC3R-SLAM, a novel…
Feed-forward 3D reconstruction has advanced rapidly, but current models remain unreliable in UAV photogrammetric acquisition. We argue that this failure is caused not only by appearance-domain shift, but also by UAV-specific camera-geometry…
3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. However, previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry, which is…
Accurate depth and camera pose estimation is essential for achieving high-quality 3D visualisations in robotic-assisted surgery. Despite recent advancements in foundation model adaptation to monocular depth estimation of endoscopic scenes…
We introduce a Generalizable Neural Radiance Field approach for predicting 3D workspace occupancy from egocentric robot observations. Unlike prior methods operating in camera-centric coordinates, our model constructs occupancy…
Transformer-based 3D reconstruction has emerged as a powerful paradigm for recovering geometry and appearance from multi-view observations, offering strong performance across challenging visual conditions. As these models scale to larger…
This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image. Geared towards high fidelity reconstruction, several recent approaches leverage implicit surface representations and deep…