Related papers: Pred-NBV: Prediction-guided Next-Best-View for 3D …

The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene using the approach from Gupta et al. [13].…

Large-scale pre-training holds the promise to advance 3D medical object detection, a crucial component of accurate computer-aided diagnosis. Yet, it remains underexplored compared to segmentation, where pre-training has already demonstrated…

3D perception tasks, such as 3D object detection and Bird's-Eye-View (BEV) segmentation using multi-camera images, have drawn significant attention recently. Despite the fact that accurately estimating both semantic and 3D scene layouts are…

Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle…

Occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing methods heavily rely on the LiDAR point clouds to generate…

Shape completion, i.e., predicting the complete geometry of an object from a partial observation, is highly relevant for several downstream tasks, most notably robotic manipulation. When basing planning or prediction of real grasps on…

Learning-based 3D object reconstruction enables single- or few-shot estimation of 3D object models. For robotics, this holds the potential to allow model-based methods to rapidly adapt to novel objects and scenes. Existing 3D reconstruction…

What makes a good viewpoint? The quality of the data used to learn 3D reconstructions is crucial for enabling efficient and accurate scene modeling. We study the active view selection problem and develop a principled analysis that yields a…

In this paper, we present an active exploration framework for high-fidelity 3D reconstruction that incrementally builds a multi-level uncertainty space and selects next-best-views through an uncertainty-driven motion planner. We introduce a…

3D reconstruction is a fundamental task in robotics that gained attention due to its major impact in a wide variety of practical settings, including agriculture, underwater, and urban environments. This task can be carried out via view…

In autonomous driving and robotics, there is a growing interest in utilizing short-term historical data to enhance multi-camera 3D object detection, leveraging the continuous and correlated nature of input video streams. Recent work has…

We present BEVCon, a simple yet effective contrastive learning framework designed to improve Bird's Eye View (BEV) perception in autonomous driving. BEV perception offers a top-down-view representation of the surrounding environment, making…

NeRFs have achieved incredible success in novel view synthesis. However, the accuracy of the implicit geometry is unsatisfactory because the passive static environmental illumination has low spatial frequency and cannot provide enough…

The performance of existing single-view 3D reconstruction methods heavily relies on large-scale 3D annotations. However, such annotations are tedious and expensive to collect. Semi-supervised learning serves as an alternative way to…

We present Deformable PV-RCNN, a high-performing point-cloud based 3D object detector. Currently, the proposal refinement methods used by the state-of-the-art two-stage detectors cannot adequately accommodate differing object scales,…

Constructing 3D representations of object geometry is critical for many robotics tasks, particularly manipulation problems. These representations must be built from potentially noisy partial observations. In this work, we focus on the…

Neural Radiance Fields (NeRFs) are gaining significant interest for online active object reconstruction due to their exceptional memory efficiency and requirement for only posed RGB inputs. Previous NeRF-based view planning methods exhibit…

Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to other 3D detectors for autonomous driving and robotics. However, transforming image features into BEV necessitates special operators to conduct feature sampling. These…

Object pose estimation is a key perceptual capability in robotics. We propose a fully-convolutional extension of the PoseCNN method, which densely predicts object translations and orientations. This has several advantages such as improving…

3D scene reconstruction from 2D images has been a long-standing task. Instead of estimating per-frame depth maps and fusing them in 3D, recent research leverages the neural implicit surface as a unified representation for 3D reconstruction.…