top of page

Object-Level SLAM / 3D Reconstruction

DistillNeRF_Wang.jpg

Paper        Video

DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
 
Letian Wang, Seung Wook Kim, Jiawei Yang, Cunjun Yu, Boris Ivanovic, Steven L. Waslander, Yue Wang, Sanja Fidler, Marco Pavone, Peter Karkus
Advances in Neural Information Processing Systems (NeurIPS), 2024.

DistillNeRF is a generalizable model for 3D scene representation, self-supervised by natural sensor streams along with distillation from offline NeRFs and vision foundation models. It also enables downstream tasks such as zero-shot 3D semantic occupancy prediction and open-vocabulary text queries.

GOM_3D_Diffusion_Liao.jpg

Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priors

Ziwei Liao, Binbin Xu, Steven L. Waslander
8th Annual Conference on Robot Learning (CoRL), 2024.

We propose a general object-level mapping system that estimates 3D object shapes (NeRFs) and poses using a 3D diffusion model as multi-categories shape priors under sparse RGB-D observations.

unc_obj_map.png

Paper       Video       Code

Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors
 
Ziwei Liao*, Jun Yang*, Jingxing Qian*, Angela P. Schoellig, and Steven L. Waslander
International Conference on Robotics and Automation (ICRA), 2024.

An uncertainty-aware object-level mapping system that can recover the 3D model, 9-DoF pose, and the state uncertainties for target unseen objects.

nbv_shiny_pose.png

Active Pose Refinement for Textureless Shiny Objects using the Structured Light Camera

Jun Yang, Jian Yao and Steven L. Waslander. 
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024.

When imaging objects are highly reflective, the structured light camera produces depth maps with missing measurements., in this work, we present an active vision framework for estimating 6D object for shiny objects.

mv_rgb_shape.png

Paper        Video

Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape Prior
 
Ziwei Liao and Steven L. Waslander
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.

We propose a 3d object modeling approach that relies on neural implicit representation and provides both an object reconstruction and an uncertainty measure for each object.

pov_slam.png

Paper       Video

POV-SLAM: Probabilistic Object-Aware Variational SLAM in Semi-Static Environments
 
Jingxing Qian, Veronica Chatrath, James Servos, Aaron Mavrinac, Wolfram Burgard, Steven L. Waslander, Angela P. Schoellig
Robotics: Science and Systems (RSS), 2023.

We propose an object-aware, factor-graph SLAM framework that tracks and reconstructs semi-static object-level changes.

mv_obj_pose.png

Paper       Video 

6D Pose Estimation for Textureless Objects on RGB Frames using Multi-View Optimization
 
Jun Yang, Wenjie Xue, Sahar Ghavidel, and Steven L. Waslander
International Conference on Robotics and Automation (ICRA), 2023.

We introduce a novel 6D object pose estimation framework that decouples the problem into a sequential two-step process. We use only RGB images acquired from multiple viewpoints.

eye-in-hand-nbv.png

Next-Best-View Selection for Robot Eye-in-Hand Calibration
 
Jun Yang, Jason Rebello, Steven L Waslander
20th Conference on Robots and Vision (CRV). IEEE, 2023.

We formulate this task as a non-linear optimization problem and introduce an active vision approach to strategically select the robot pose for maximizing calibration accuracy.

dynamic_mapping.png

Paper       Video

POCD: Probabilistic Object-Level Change Detection and Volumetric Mapping in Semi-Static Scenes
 
Jingxing Qian*, Veronica Chatrath*, Jun Yang, James Servos, Angela P Schoellig, Steven L Waslander
Robotics: Science and Systems (RSS). 2022.

We propose a framework that introduces a novel probabilistic object state representation to track object pose changes in semi-static scenes.

NBV_Shiny.png

Paper       Video

Next-Best-View (NBV) Prediction for Highly Reflective Objects
 
Jun Yang and Steven L. Waslander
International Conference on Robotics and Automation (ICRA), 2022

In this work, we propose a next-best-view framework to strategically select camera viewpoints for completing depth data on reflective objects.

fusion.png

Paper      Video

Probabilistic Multi-View Fusion  of Active Stereo Depth Maps
​
Jun Yang, Dong Li and Steven L. Waslander. 
IEEE Robotics and Automation Letters (RA-L), 2021
​
In this work, we propose a probabilistic framework for scene reconstruction in robotic bin-picking. We estimate the depth data uncertainty and incorporated into a probabilistic model for  incrementally updating the scene.

robi_project.png

Paper       Video

ROBI: Reflective Object In Bins Dataset

Jun Yang, Yizhou Gao, Dong Li and Steven L. Waslander.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.

In this paper, we present the ROBI dataset, a public dataset for 6D object pose estimation and multi-view depth fusion.. The dataset includes texture-less, highly reflective industrial parts in robotic bin-picking scenarios.

bottom of page