MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis
- URL: http://arxiv.org/abs/2501.06660v1
- Date: Sat, 11 Jan 2025 23:16:49 GMT
- Title: MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis
- Authors: Hengyuan Zhang, David Paz, Yuliang Guo, Xinyu Huang, Henrik I. Christensen, Liu Ren,
- Abstract summary: We propose a novel framework leveraging Gaussian splatting to reconstruct scenes and render camera images in target sensor configurations.
Our proposed framework on the nuScenes and Argoverse 2 datasets demonstrates a performance improvement of 18% through effective dataset augmentation.
This enables data reuse and reduces the need for laborious data labeling.
- Score: 15.64243217749911
- License:
- Abstract: Online mapping reduces the reliance of autonomous vehicles on high-definition (HD) maps, significantly enhancing scalability. However, recent advancements often overlook cross-sensor configuration generalization, leading to performance degradation when models are deployed on vehicles with different camera intrinsics and extrinsics. With the rapid evolution of novel view synthesis methods, we investigate the extent to which these techniques can be leveraged to address the sensor configuration generalization challenge. We propose a novel framework leveraging Gaussian splatting to reconstruct scenes and render camera images in target sensor configurations. The target config sensor data, along with labels mapped to the target config, are used to train online mapping models. Our proposed framework on the nuScenes and Argoverse 2 datasets demonstrates a performance improvement of 18% through effective dataset augmentation, achieves faster convergence and efficient training, and exceeds state-of-the-art performance when using only 25% of the original training data. This enables data reuse and reduces the need for laborious data labeling. Project page at https://henryzhangzhy.github.io/mapgs.
Related papers
- Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles [81.29018359825872]
This paper consolidates a set of good practices to finetune large pretrained models for a real-world task.
Specifically, we develop several strategies to account for discrepancies between the synthetic data and real driving data.
Our insights lead to effective finetuning that results in a $68.8%$ reduction in FID for novel view synthesis over prior arts.
arXiv Detail & Related papers (2024-12-19T03:39:13Z) - Improving Object Detection by Modifying Synthetic Data with Explainable AI [3.0519884745675485]
We propose a novel conceptual approach to improve the performance of computer vision models trained on synthetic images.
We use robust Explainable AI (XAI) techniques to guide the modification of 3D models used to generate these images.
We show that synthetic data can improve detection of vehicles in orientations unseen in training by 4.6%.
arXiv Detail & Related papers (2024-12-02T13:24:43Z) - Digi2Real: Bridging the Realism Gap in Synthetic Data Face Recognition via Foundation Models [4.910937238451485]
We introduce a novel framework for realism transfer aimed at enhancing the realism of synthetically generated face images.
By integrating the controllable aspects of the graphics pipeline with our realism enhancement technique, we generate a large amount of realistic variations.
arXiv Detail & Related papers (2024-11-04T15:42:22Z) - SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurations [3.8472678261304587]
We propose a modular pipeline for vector map generation with improved generalization to sensor configurations.
By adopting a BEV semantic map robust to different sensor configurations, our proposed approach significantly improves the generalization performance.
arXiv Detail & Related papers (2024-04-30T23:45:16Z) - Fast Non-Rigid Radiance Fields from Monocularized Data [66.74229489512683]
This paper proposes a new method for full 360deg inward-facing novel view synthesis of non-rigidly deforming scenes.
At the core of our method are 1) An efficient deformation module that decouples the processing of spatial and temporal information for accelerated training and inference; and 2) A static module representing the canonical scene as a fast hash-encoded neural radiance field.
In both cases, our method is significantly faster than previous methods, converging in less than 7 minutes and achieving real-time framerates at 1K resolution, while obtaining a higher visual accuracy for generated novel views.
arXiv Detail & Related papers (2022-12-02T18:51:10Z) - LaMAR: Benchmarking Localization and Mapping for Augmented Reality [80.23361950062302]
We introduce LaMAR, a new benchmark with a comprehensive capture and GT pipeline that co-registers realistic trajectories and sensor streams captured by heterogeneous AR devices.
We publish a benchmark dataset of diverse and large-scale scenes recorded with head-mounted and hand-held AR devices.
arXiv Detail & Related papers (2022-10-19T17:58:17Z) - Dynamic Spatial Sparsification for Efficient Vision Transformers and
Convolutional Neural Networks [88.77951448313486]
We present a new approach for model acceleration by exploiting spatial sparsity in visual data.
We propose a dynamic token sparsification framework to prune redundant tokens.
We extend our method to hierarchical models including CNNs and hierarchical vision Transformers.
arXiv Detail & Related papers (2022-07-04T17:00:51Z) - When Vision Transformers Outperform ResNets without Pretraining or
Strong Data Augmentations [111.44860506703307]
Vision Transformers (ViTs) and existing VisionNets signal efforts on replacing hand-wired features or inductive throughputs with general-purpose neural architectures.
This paper investigates ViTs and Res-Mixers from the lens of loss geometry, intending to improve the models' data efficiency at training and inference.
We show that the improved robustness attributes to sparser active neurons in the first few layers.
The resultant ViTs outperform Nets of similar size and smoothness when trained from scratch on ImageNet without large-scale pretraining or strong data augmentations.
arXiv Detail & Related papers (2021-06-03T02:08:03Z) - Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with
Transformers [115.90778814368703]
Our objective is language-based search of large-scale image and video datasets.
For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval scales.
An alternative approach of using vision-text transformers with cross-attention gives considerable improvements in accuracy over the joint embeddings.
arXiv Detail & Related papers (2021-03-30T17:57:08Z) - PennSyn2Real: Training Object Recognition Models without Human Labeling [12.923677573437699]
We propose PennSyn2Real - a synthetic dataset consisting of more than 100,000 4K images of more than 20 types of micro aerial vehicles (MAVs)
The dataset can be used to generate arbitrary numbers of training images for high-level computer vision tasks such as MAV detection and classification.
We show that synthetic data generated using this framework can be directly used to train CNN models for common object recognition tasks such as detection and segmentation.
arXiv Detail & Related papers (2020-09-22T02:53:40Z) - Virtual to Real adaptation of Pedestrian Detectors [9.432150710329607]
ViPeD is a new synthetically generated set of images collected with the graphical engine of the video game GTA V - Grand Theft Auto V.
We propose two different Domain Adaptation techniques suitable for the pedestrian detection task, but possibly applicable to general object detection.
Experiments show that the network trained with ViPeD can generalize over unseen real-world scenarios better than the detector trained over real-world data.
arXiv Detail & Related papers (2020-01-09T14:50:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.