City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation

2022-09-28 · Yongliang Shi, Runyi Yang, Pengfei Li, Zirui Wu, Hao Zhao, Guyue Zhou

Neural implicit representations are drawing a lot of attention from the robotics community recently, as they are expressive, continuous and compact. However, city-scale continual implicit dense mapping based on sparse LiDAR input is still an under-explored challenge. To this end, we successfully build a city-scale continual neural mapping system with a panoptic representation that consists of environment-level and instance-level modelling. Given a stream of sparse LiDAR point cloud, it maintains a dynamic generative model that maps 3D coordinates to signed distance field (SDF) values. To address the difficulty of representing geometric information at different levels in city-scale space, we propose a tailored three-layer sampling strategy to dynamically sample the global, local and near-surface domains. Meanwhile, to realize high fidelity mapping of instance under incomplete observation, category-specific prior is introduced to better model the geometric details. We evaluate on the public SemanticKITTI dataset and demonstrate the significance of the newly proposed three-layer sampling strategy and panoptic representation, using both quantitative and qualitative results. Codes and model will be publicly available.

📄 PDF Abstract BibTeX arXiv:2209.14072

Code (0)

등록된 구현이 없습니다.

PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning

2022-09-14 · Grégoire Petit, Adrian Popescu, Eden Belouadah, David Picard 외

Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a compromise between these two properties is part…

class-incremental learning Class Incremental Learning Exemplar-Free Incremental Learning+1

Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling

2026-04-21 · Weijie Zhao, Mingquan Liu, Bolun Wang, Simo Wu 외 arxiv

Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identify the primary bottleneck in the attentio…

NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping

2023-03-19 · ICCV 2023 1 · Junyuan Deng, Xieyuanli Chen, Songpengcheng Xia, Zhen Sun 외

Simultaneously odometry and mapping using LiDAR data is an important task for mobile systems to achieve full autonomy in large-scale environments. However, most existing LiDAR-based methods prioritize tracking quality ov…

NeRF

Incremental Learning Using Conditional Adversarial Networks

2019-10-01 · ICCV 2019 10 · Ye Xiang, Ying Fu, Pan Ji, Hua Huang

Incremental learning using Deep Neural Networks (DNNs) suffers from catastrophic forgetting. Existing methods mitigate it by either storing old image examples or only updating a few fully connected layers of DNNs, which,…

Incremental Learning

Class Incremental Learning with Pre-trained Vision-Language Models

2023-10-31 · Xialei Liu, Xusheng Cao, Haori Lu, Jia-Wen Xiao 외

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language mode…

class-incremental learning Class Incremental Learning Continual Learning Incremental Learning+1