Search Results for author:
Found 11 papers, 6 papers with code
FASIONAD : FAst and Slow FusION Thinking Systems for Human-Like Autonomous Driving with Adaptive Feedback
FASIONAD achieves state-of-the-art performance on this benchmark, establishing a new standard for frameworks integrating fast and slow cognitive processes in autonomous driving.
EFFOcc: A Minimal Baseline for EFficient Fusion-based 3D Occupancy Network
On Occ3D-nuScenes benchmark, EFFOcc has only 18. 4M parameters, and achieves 50. 46 in terms of mean IoU (mIoU), to our knowledge, it is the occnet with minimal parameters compared with related occnets.
PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving
For foreground instance grouping, we propose a novel 3D instance mask decoder that can efficiently extract individual objects.
SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation
To this end, we explore the sparse representation and review the task design for end-to-end autonomous driving, proposing a new paradigm named SparseDrive.
From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers
We then introduce Attention Bias Calibration (ABC), a calibration stage that enables the model to automatically learn the proper attention biases, which we show to be connected to mechanisms in relative position encoding.
Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review
Given the lack of current surveys for this rapidly expanding field, we present a hierarchically-structured review of grid-centric perception for autonomous vehicles.
StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation
Predicting the future occupancy states of the surrounding environment is a vital task for autonomous driving.
Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detection
A novel method that realizes the feature-level fusion under the bird's-eye view (BEV) for a better feature representation is proposed.
SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and Tracking
Our novel sparse feature sampling module only utilizes local 2D region of interest (RoI) features calculated by the projection of 3D query boxes for further box refinement, leading to a fully-convolutional and deployment-friendly pipeline.
Ranked #8 on
Robust Camera Only 3D Object Detection
on nuScenes-C
Soundify: Matching Sound Effects to Video
In the art of video editing, sound helps add character to an object and immerse the viewer within a space.
HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework
Embedding models have been an effective learning paradigm for high-dimensional data.
