Hongyang Li

35

Papers

308

Total Citations

1

Affiliations

Affiliations

Peking University

Papers (35)

Generalized Predictive Model for Autonomous Driving

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation

Visual In-Context Prompting

Detect Anything 3D in the Wild

ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models

Decoupled Diffusion Sparks Adaptive Scene Generation

Visual Point Cloud Forecasting enables Scalable Autonomous Driving

FastMAC: Stochastic Spectral Sampling of Correspondence Graph

Monocular 3D Object Detection: An Extrinsic Parameter Free Approach

Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search

Exploring intermediate representation for monocular vehicle pose estimation

Align Representations With Base: A New Approach to Self-Supervised Learning

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision

Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection

Think Twice Before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving

Stare at What You See: Masked Image Modeling Without Reconstruction

Planning-Oriented Autonomous Driving

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

Scene as Occupancy

Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach

Density-invariant Features for Distant Point Cloud Registration

DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting

DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving

Detection Transformer with Stable Matching

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers

DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation

ST-P3: End-to-End Vision-Based Autonomous Driving via Spatial-Temporal Feature Learning

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark

ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding

NeurIPS 2020arXiv

Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space

NeurIPS 2021arXiv

Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline

NeurIPS 2022arXiv

OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping

NeurIPS 2023arXiv

Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection

NeurIPS 2023arXiv