Towards Efficient and Effective Multi-Camera Encoding for End-to-End Driving

• URL: http://arxiv.org/abs/2512.10947v2
• Date: Fri, 12 Dec 2025 19:16:02 GMT
• Title: Towards Efficient and Effective Multi-Camera Encoding for End-to-End Driving
• Authors: Jiawei Yang, Ziyu Chen, Yurong You, Yan Wang, Yiming Li, Yuxiao Chen, Boyi Li, Boris Ivanovic, Marco Pavone, Yue Wang,
• Abstract summary: We present Flex, an efficient and effective scene encoder that addresses the computational bottleneck of processing high-volume multi-camera data in autonomous driving.<n>By design, our approach is geometry-agnostic, learning a compact scene representation directly from data without relying on the explicit 3D inductive biases.<n>Our findings challenge the prevailing assumption that 3D priors are necessary, demonstrating that a data-driven, joint encoding strategy offers a more scalable, efficient and effective path for future autonomous driving systems.
• Score: 54.85072592658933
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Flex, an efficient and effective scene encoder that addresses the computational bottleneck of processing high-volume multi-camera data in end-to-end autonomous driving. Flex employs a small set of learnable scene tokens to jointly encode information from all image tokens across different cameras and timesteps. By design, our approach is geometry-agnostic, learning a compact scene representation directly from data without relying on the explicit 3D inductive biases, such as Bird-Eye-View (BEV), occupancy or tri-plane representations, which are common in prior work. This holistic encoding strategy aggressively compresses the visual input for the downstream Large Language Model (LLM) based policy model. Evaluated on a large-scale proprietary dataset of 20,000 driving hours, our Flex achieves 2.2x greater inference throughput while improving driving performance by a large margin compared to state-of-the-art methods. Furthermore, we show that these compact scene tokens develop an emergent capability for scene decomposition without any explicit supervision. Our findings challenge the prevailing assumption that 3D priors are necessary, demonstrating that a data-driven, joint encoding strategy offers a more scalable, efficient and effective path for future autonomous driving systems.

Related papers

• X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability [49.4647778989539]
  X-Scene is a novel framework for large-scale driving scene generation.<n>It achieves both geometric intricacy and appearance fidelity, while offering flexible controllability.<n>X-Scene significantly advances controllability and fidelity for large-scale driving scene generation.
  arXiv  Detail & Related papers  (2025-06-16T14:43:18Z)
• Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving [33.2092963387255]
  Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures.<n>We present an efficient triplane-based multi-camera tokenization strategy that leverages recent advances in 3D neural reconstruction and rendering.<n> Experiments on a large-scale AV dataset and state-of-the-art neural simulator demonstrate that our approach yields significant savings over current image patch-based tokenization strategies.
  arXiv  Detail & Related papers  (2025-06-13T21:56:52Z)
• InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression [1.8893427856534721]
  We propose InternVL-X, which outperforms the InternVL model in both performance and efficiency.<n>By utilizing 20% or fewer visual tokens, InternVL-X achieves state-of-the-art performance on 7 public MLLM benchmarks, and improves the average metric by 2.34% across 12 tasks.
  arXiv  Detail & Related papers  (2025-03-27T09:31:35Z)
• LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving [88.85002707211777]
  LargeAD is a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets.<n>Our framework leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds.<n>This alignment facilitates cross-modal representation learning, enhancing the semantic consistency between 2D and 3D data.
  arXiv  Detail & Related papers  (2025-01-07T18:59:59Z)
• VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving [44.91443640710085]
  VisionPAD is a novel self-supervised pre-training paradigm for vision-centric algorithms in autonomous driving.<n>It reconstructs multi-view representations using only images as supervision.<n>It significantly improves performance in 3D object detection, occupancy prediction and map segmentation.
  arXiv  Detail & Related papers  (2024-11-22T03:59:41Z)
• DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation [10.296670127024045]
  DriveScape is an end-to-end framework for multi-view, 3D condition-guided video generation. Our Bi-Directional Modulated Transformer (BiMot) ensures precise alignment of 3D structural information. DriveScape excels in video generation performance, achieving state-of-the-art results on the nuScenes dataset with an FID score of 8.34 and an FVD score of 76.39.
  arXiv  Detail & Related papers  (2024-09-09T09:43:17Z)
• AutoDecoding Latent 3D Diffusion Models [95.7279510847827]
  We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations.
  arXiv  Detail & Related papers  (2023-07-07T17:59:14Z)
• High Fidelity Image Synthesis With Deep VAEs In Latent Space [0.0]
  We present fast, realistic image generation on high-resolution, multimodal datasets using hierarchical variational autoencoders (VAEs) In this two-stage setup, the autoencoder compresses the image into its semantic features, which are then modeled with a deep VAE. We demonstrate the effectiveness of our two-stage approach, achieving a FID of 9.34 on the ImageNet-256 dataset which is comparable to BigGAN.
  arXiv  Detail & Related papers  (2023-03-23T23:45:19Z)
• Policy Pre-training for End-to-end Autonomous Driving via Self-supervised Geometric Modeling [96.31941517446859]
  We propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only.
  arXiv  Detail & Related papers  (2023-01-03T08:52:49Z)
• Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation [77.60050239225086]
  We propose an effective training data generation process by fitting a 3D car model with dynamic parts to vehicles in real images. Our approach is fully automatic without any human interaction. We present a multi-task network for VUS parsing and a multi-stream network for VHI parsing.
  arXiv  Detail & Related papers  (2020-12-15T03:03:38Z)

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.