3D Object Detection

571 papers with code • 55 benchmarks • 48 datasets

3D Object Detection is a task in computer vision where the goal is to identify and locate objects in a 3D environment based on their shape, location, and orientation. It involves detecting the presence of objects and determining their location in the 3D space in real-time. This task is crucial for applications such as autonomous vehicles, robotics, and augmented reality.

( Image credit: AVOD )

Libraries

Use these libraries to find 3D Object Detection models and implementations

Latest papers with no code

GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection

no code yet • 18 Mar 2024

Additionally, we propose a Global Align module to rectify the misalignment between LiDAR and camera BEV features.

EffiPerception: an Efficient Framework for Various Perception Tasks

no code yet • 18 Mar 2024

The accuracy-speed-memory trade-off is always the priority to consider for several computer vision perception tasks.

V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions

no code yet • 17 Mar 2024

Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection.

SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras

no code yet • 15 Mar 2024

The field of autonomous driving has attracted considerable interest in approaches that directly infer 3D objects in the Bird's Eye View (BEV) from multiple cameras.

SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception

no code yet • 15 Mar 2024

The versatility of SparseFusion is also validated in the temporal object detection task and 3D lane detection task.

Improving Distant 3D Object Detection Using 2D Box Supervision

no code yet • 14 Mar 2024

This mapping allows the depth estimation of distant objects conditioned on their 2D boxes, making long-range 3D detection with 2D supervision feasible.

PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest

no code yet • 14 Mar 2024

In this work, we present PoIFusion, a simple yet effective multi-modal 3D object detection framework to fuse the information of RGB images and LiDAR point clouds at the point of interest (abbreviated as PoI).

CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow

no code yet • 13 Mar 2024

Autonomous driving stands as a pivotal domain in computer vision, shaping the future of transportation.

Eliminating Cross-modal Conflicts in BEV Space for LiDAR-Camera 3D Object Detection

no code yet • 12 Mar 2024

Recent 3D object detectors typically utilize multi-sensor data and unify multi-modal features in the shared bird's-eye view (BEV) representation space.

SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection

no code yet • 12 Mar 2024

Sparse 3D detectors have received significant attention since the query-based paradigm embraces low latency without explicit dense BEV feature construction.