Search Results for author:
Found 11 papers, 5 papers with code
Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) has marked a significant breakthrough in the realm of 3D scene reconstruction and novel view synthesis.
Language-Assisted 3D Scene Understanding
The scale and quality of point cloud datasets constrain the advancement of point cloud learning.
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
This paper presents GIR, a 3D Gaussian Inverse Rendering method for relightable scene factorization.
UniQuadric: A SLAM Backend for Unknown Rigid Object 3D Tracking and Light-Weight Modeling
Subsequently, in the part of object state estimation, we propose a tightly coupled optimization model for object pose and scale estimation, incorporating hybrids constraints into a novel dual sliding window optimization framework for joint estimation.
An Object SLAM Framework for Association, Mapping, and High-Level Tasks
Taking into consideration the semantic invariance of objects, we convert the object map to a topological map to provide semantic descriptors to enable multi-map matching.
Implicit Neural Representation for Cooperative Low-light Image Enhancement
Finally, extensive experiments demonstrate the robustness and superior effectiveness of our proposed NeRCo.
BSH-Det3D: Improving 3D Object Detection with BEV Shape Heatmap
Specifically, we design the Pillar-based Shape Completion (PSC) module to predict the probability of occupancy whether a pillar contains object shapes.
Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning
In this work, we attempt to learn an object-compositional neural implicit representation for editable scene rendering by leveraging labels inferred from the off-the-shelf 2D panoptic segmentation networks instead of the ground truth annotations.
Object SLAM-Based Active Mapping and Robotic Grasping
The framework is built on an object SLAM system integrated with a simultaneous multi-object pose estimation process that is optimized for robotic grasping.
EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association
Object-level data association and pose estimation play a fundamental role in semantic SLAM, which remain unsolved due to the lack of robust and accurate algorithms.
