MoST: Multi-modality Scene Tokenization for Motion Prediction

• URL: http://arxiv.org/abs/2404.19531v1
• Date: Tue, 30 Apr 2024 13:09:41 GMT
• Title: MoST: Multi-modality Scene Tokenization for Motion Prediction
• Authors: Norman Mu, Jingwei Ji, Zhenpei Yang, Nate Harada, Haotian Tang, Kan Chen, Charles R. Qi, Runzhou Ge, Kratarth Goel, Zoey Yang, Scott Ettinger, Rami Al-Rfou, Dragomir Anguelov, Yin Zhou,
• Abstract summary: We propose tokenizing the visual world into a compact set of scene elements. We then leverage pre-trained image foundation models and LiDAR neural networks to encode all the scene elements in an open-vocabulary manner. Our proposed representation can efficiently encode the multi-frame multi-modality observations with a few hundred tokens.
• Score: 39.97334929667033
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many existing motion prediction approaches rely on symbolic perception outputs to generate agent trajectories, such as bounding boxes, road graph information and traffic lights. This symbolic representation is a high-level abstraction of the real world, which may render the motion prediction model vulnerable to perception errors (e.g., failures in detecting open-vocabulary obstacles) while missing salient information from the scene context (e.g., poor road conditions). An alternative paradigm is end-to-end learning from raw sensors. However, this approach suffers from the lack of interpretability and requires significantly more training resources. In this work, we propose tokenizing the visual world into a compact set of scene elements and then leveraging pre-trained image foundation models and LiDAR neural networks to encode all the scene elements in an open-vocabulary manner. The image foundation model enables our scene tokens to encode the general knowledge of the open world while the LiDAR neural network encodes geometry information. Our proposed representation can efficiently encode the multi-frame multi-modality observations with a few hundred tokens and is compatible with most transformer-based architectures. To evaluate our method, we have augmented Waymo Open Motion Dataset with camera embeddings. Experiments over Waymo Open Motion Dataset show that our approach leads to significant performance improvements over the state-of-the-art.

Related papers

• VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation [66.00245701441547]
  We introduce a novel approach to reduce vision compute by leveraging redundant vision tokens "skipping layers" rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video.
  arXiv  Detail & Related papers  (2024-08-29T17:21:58Z)
• uTRAND: Unsupervised Anomaly Detection in Traffic Trajectories [5.6328191854587395]
  We present a framework called uTRAND, that shifts the problem of anomalous trajectory prediction from the pixel space to a semantic-topological domain. We show that uTRAND outperforms other state-of-the-art approaches on a dataset of anomalous trajectories collected in a real-world setting.
  arXiv  Detail & Related papers  (2024-04-19T08:46:33Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)
• Factored Neural Representation for Scene Understanding [39.66967677639173]
  We introduce a factored neural scene representation that can directly be learned from a monocular RGB-D video to produce object-level neural presentations. We evaluate ours against a set of neural approaches on both synthetic and real data to demonstrate that the representation is efficient, interpretable, and editable.
  arXiv  Detail & Related papers  (2023-04-21T13:40:30Z)
• 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)
• Wide and Narrow: Video Prediction from Context and Motion [54.21624227408727]
  We propose a new framework to integrate these complementary attributes to predict complex pixel dynamics through deep networks. We present global context propagation networks that aggregate the non-local neighboring representations to preserve the contextual information over the past frames. We also devise local filter memory networks that generate adaptive filter kernels by storing the motion of moving objects in the memory.
  arXiv  Detail & Related papers  (2021-10-22T04:35:58Z)
• Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild [31.40575057347465]
  We tackle the task of video-based visual emotion recognition in the wild. Standard methodologies that rely solely on the extraction of bodily and facial features often fall short of accurate emotion prediction. We aspire to alleviate this problem by leveraging visual context in the form of scene characteristics and attributes.
  arXiv  Detail & Related papers  (2021-05-16T17:31:59Z)
• Optical Flow Estimation from a Single Motion-blurred Image [66.2061278123057]
  Motion blur in an image may have practical interests in fundamental computer vision problems. We propose a novel framework to estimate optical flow from a single motion-blurred image in an end-to-end manner.
  arXiv  Detail & Related papers  (2021-03-04T12:45:18Z)
• Contextual Encoder-Decoder Network for Visual Saliency Prediction [42.047816176307066]
  We propose an approach based on a convolutional neural network pre-trained on a large-scale image classification task. We combine the resulting representations with global scene information for accurately predicting visual saliency. Compared to state of the art approaches, the network is based on a lightweight image classification backbone.
  arXiv  Detail & Related papers  (2019-02-18T16:15:25Z)

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.