Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation

• URL: http://arxiv.org/abs/2406.01349v3
• Date: Thu, 6 Jun 2024 17:39:50 GMT
• Title: Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation
• Authors: Enhui Ma, Lijun Zhou, Tao Tang, Zhan Zhang, Dong Han, Junpeng Jiang, Kun Zhan, Peng Jia, Xianpeng Lang, Haiyang Sun, Di Lin, Kaicheng Yu,
• Abstract summary: We propose a novel diffusion-based long video generation method with a shared noise modeling mechanism across the multi-views to increase spatial consistency. Our method can generate up to 40 frames of video without loss of consistency which is about 5 times longer compared with state-of-the-art methods. Our framework is able to go beyond perception and prediction tasks, for the first time, boost the planning performance of the end-to-end autonomous driving model by a margin of 25%.
• Score: 20.88042649759396
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail to improve the performance of planning of end-to-end autonomous driving models as the generated videos are usually less than 8 frames and the spatial and temporal inconsistencies are not negligible. To this end, we propose Delphi, a novel diffusion-based long video generation method with a shared noise modeling mechanism across the multi-views to increase spatial consistency, and a feature-aligned module to achieves both precise controllability and temporal consistency. Our method can generate up to 40 frames of video without loss of consistency which is about 5 times longer compared with state-of-the-art methods. Instead of randomly generating new data, we further design a sampling policy to let Delphi generate new data that are similar to those failure cases to improve the sample efficiency. This is achieved by building a failure-case driven framework with the help of pre-trained visual language models. Our extensive experiment demonstrates that our Delphi generates a higher quality of long videos surpassing previous state-of-the-art methods. Consequentially, with only generating 4% of the training dataset size, our framework is able to go beyond perception and prediction tasks, for the first time to the best of our knowledge, boost the planning performance of the end-to-end autonomous driving model by a margin of 25%.

Related papers

• Minimum Tuning to Unlock Long Output from LLMs with High Quality Data as the Key [3.3339400603549265]
  We show that it is possible to achieve notable performance improvement in tuned models with a small fraction of training data instances and compute. Our findings suggest that, while capacities for generating long output vary across different models out-of-the-box, our approach to tune them with high-quality data using lite compute, consistently yields notable improvement across all models we experimented on.
  arXiv  Detail & Related papers  (2024-10-14T07:09:02Z)
• AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving [68.73885845181242]
  We propose an Automatic Data Engine (AIDE) that automatically identifies issues, efficiently curates data, improves the model through auto-labeling, and verifies the model through generation of diverse scenarios. We further establish a benchmark for open-world detection on AV datasets to comprehensively evaluate various learning paradigms, demonstrating our method's superior performance at a reduced cost.
  arXiv  Detail & Related papers  (2024-03-26T04:27:56Z)
• RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks [93.18404922542702]
  We present a novel video generative model designed to address long-term spatial and temporal dependencies. Our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks. Our model synthesizes high-fidelity video clips at a resolution of $256times256$ pixels, with durations extending to more than $5$ seconds at a frame rate of 30 fps.
  arXiv  Detail & Related papers  (2024-01-11T16:48:44Z)
• TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement [64.11385310305612]
  We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence. Our approach employs two stages: (1) a matching stage, which independently locates a suitable candidate point match for the query point on every other frame, and (2) a refinement stage, which updates both the trajectory and query features based on local correlations. The resulting model surpasses all baseline methods by a significant margin on the TAP-Vid benchmark, as demonstrated by an approximate 20% absolute average Jaccard (AJ) improvement on DAVIS.
  arXiv  Detail & Related papers  (2023-06-14T17:07:51Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. This creates a barrier to fusing knowledge across individual models to yield a better single model. We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• Flexible Diffusion Modeling of Long Videos [15.220686350342385]
  We introduce a generative model that can at test-time sample any arbitrary subset of video frames conditioned on any other subset. We demonstrate improved video modeling over prior work on a number of datasets and sample temporally coherent videos over 25 minutes in length. We additionally release a new video modeling dataset and semantically meaningful metrics based on videos generated in the CARLA self-driving car simulator.
  arXiv  Detail & Related papers  (2022-05-23T17:51:48Z)
• STAR: Sparse Transformer-based Action Recognition [61.490243467748314]
  This work proposes a novel skeleton-based human action recognition model with sparse attention on the spatial dimension and segmented linear attention on the temporal dimension of data. Experiments show that our model can achieve comparable performance while utilizing much less trainable parameters and achieve high speed in training and inference.
  arXiv  Detail & Related papers  (2021-07-15T02:53:11Z)
• Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction [79.23730812282093]
  We introduce Greedy Hierarchical Variational Autoencoders (GHVAEs), a method that learns high-fidelity video predictions by greedily training each level of a hierarchical autoencoder. GHVAEs provide 17-55% gains in prediction performance on four video datasets, a 35-40% higher success rate on real robot tasks, and can improve performance monotonically by simply adding more modules.
  arXiv  Detail & Related papers  (2021-03-06T18:58:56Z)
• Transformation-based Adversarial Video Prediction on Large-Scale Data [19.281817081571408]
  We focus on the task of video prediction, where given a sequence of frames extracted from a video, the goal is to generate a plausible future sequence. We first improve the state of the art by performing a systematic empirical study of discriminator decompositions. We then propose a novel recurrent unit which transforms its past hidden state according to predicted motion-like features.
  arXiv  Detail & Related papers  (2020-03-09T10:52:25Z)

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.