Are we ready for autonomous driving? The KITTI vision benchmark suite

No abstract is available for this paper.

• Publication year

  2012

• Venue

  2012 IEEE Conference on Computer Vision and Pattern Recognition

• Publication date

  2012-06-16

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/CVPR.2012.6248074
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Continuous Markov Random Fields for Robust Stereo Estimation

  2012cited by this paper
• Automatic camera and range sensor calibration using a single shot

  2012cited by this paper
• Pedestrian Detection: An Evaluation of the State of the Art

  2012cited by this paper
• Pushing the limits of stereo using variational stereo estimation

  2012cited by this paper
• Ford Campus vision and lidar data set

  2011cited by this paper
• Fast cost-volume filtering for visual correspondence and beyond

  2011influential reference
• Towards a benchmark for RGB-D SLAM evaluation

  2011cited by this paper
• StereoScan: Dense 3d reconstruction in real-time

  2011influential reference
• A new benchmark for stereo-based pedestrian detection

  2011cited by this paper
• LIBSVM: A library for support vector machines

  2011influential reference
• Object Detection with Discriminatively Trained Part Based Models

  2010cited by this paper
• Efficient Large-Scale Stereo Matching

  2010cited by this paper
• Secrets of optical flow estimation and their principles

  2010influential reference
• Joint Optimisation for Object Class Segmentation and Dense Stereo Reconstruction

  2010cited by this paper
• Visual odometry priors for robust EKF-SLAM

  2010cited by this paper
• Ground Truth Evaluation of Stereo Algorithms for Real World Applications

  2010cited by this paper
• Pose estimation for category specific multiview object localization

  2009cited by this paper
• On measuring the accuracy of SLAM algorithms

  2009influential reference
• Flow separation for fast and robust stereo odometry

  2009cited by this paper
• Generic and real-time structure from motion using local bundle adjustment

  2009cited by this paper
• A collection of outdoor robotic datasets with centimeter-accuracy ground truth

  2009cited by this paper
• The New College Vision and Laser Data Set

  2009cited by this paper
• LabelMe: A Database and Web-Based Tool for Image Annotation

  2008cited by this paper
• A Database and Evaluation Methodology for Optical Flow

  2007influential reference
• A Duality Based Approach for Realtime TV-L1 Optical Flow

  2007cited by this paper
• Efficient Sampling of Disparity Space for Fast And Accurate Matching

  2007cited by this paper
• Depth Estimation Using Monocular and Stereo Cues

  2007cited by this paper
• A Real-Time-capable Hard-and Software Architecture for Joint Image and Knowledge Processing in Cognitive Automobiles

  2007cited by this paper
• Depth and Appearance for Mobile Scene Analysis

  2007cited by this paper
• The Pascal Visual Object Classes Challenge 2006 ( VOC 2006 ) Results

  2006cited by this paper
• Street Scenes: towards scene understanding in still images

  2006cited by this paper
• The PASCAL Visual Object Classes Challenge

  2006cited by this paper
• Evaluation of Features Detectors and Descriptors based on 3D Objects

  2005cited by this paper
• Histograms of oriented gradients for human detection

  2005cited by this paper
• Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

  2004cited by this paper
• High Accuracy Optical Flow Estimation Based on a Theory for Warping

  2004cited by this paper
• Stratified Dense Matching for Stereopsis in Complex Scenes

  2003cited by this paper
• Computing visual correspondence with occlusions using graph cuts

  2001cited by this paper
• A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

  2001influential reference
• Pyramidal implementation of the lucas kanade feature tracker

  1999cited by this paper
• Simultaneous robot-world and hand-eye calibration

  1998cited by this paper
• Columbia Object Image Library (COIL100)

  1996influential reference
• "Determining optical flow": A Retrospective

  1993cited by this paper
• Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation

  year unknowncited by this paper
• Author manuscript, published in "IEEE Conference on Computer Vision and Pattern Recognition (CVPR '11) (2011)" Scene Flow Estimation by Growing Correspondence Seeds

  year unknowncited by this paper

• Experience and Adaptation in AI-mediated Hiring Systems: A Combined Analysis of Online Discourse and Interface Design

  2026cites this paper
• Robust multimodal 3D object detection: overcoming weather challenges in autonomous driving perception systems

  2026cites this paper
• 3D Multi-Object Tracking Driven by Multi-Level Association and Intelligent Filtering

  2026cites this paper
• StableDPT: Temporal Stable Monocular Video Depth Estimation

  2026cites this paper
• PSKNet: Lightweight kernel-aware slice network for real-time stereo depth estimation on edge devices

  2026cites this paper
• Shape Enhanced Network With Transformer-Based Completion for LiDAR-Based 3D Detection From Point Cloud

  2026cites this paper
• HSR-VINS: Hybrid Structural Regularities for Robust Visual–Inertial Navigation System

  2026cites this paper
• Multi-scale hierarchical voxel-aware transformer network for 3D object detection in open-pit mines

  2026cites this paper
• Future object localization using multi-modal ego-centric video

  2026cites this paper
• DAPU: Distribution-aware patch upsampling for point cloud-based 3D object detection

  2026cites this paper
• Offset-corrected query generation strategies for cross-modality misalignment in 3D object detection: aligning LiDAR and camera

  2026cites this paper
• RSLCPP - Deterministic Simulations Using ROS 2

  2026cites this paper
• Bipartite Mode Matching for Vision Training Set Search from a Hierarchical Data Server

  2026cites this paper
• CPFSSR: Combined permuted self-attention and fast Fourier transform-based network for stereo image super-resolution

  2026cites this paper
• RefreshReg: Receptive Field Reshaping and Multi-Layer Consistency Filtering for Point Cloud Registration

  2026cites this paper
• HiGS-Calib: A Hierarchical 3D Gaussian Splatting-Based Targetless Local-Consistent LiDAR-Camera Calibration Method

  2026cites this paper
• DepthVision3D: A versatile deep learning dataset for 3D vision

  2026cites this paper
• A dual-branch noise-resistant sparse convolution method for multi-modal 3D object detection in autonomous driving

  2026cites this paper
• Artificial Intelligence-driven visual attention framework for vehicle-pedestrian interaction in Intelligent Transportation System

  2026cites this paper
• 3D multi-vehicle tracking in highway scenarios via candidates fusion network with camera-LIDAR deep association

  2026cites this paper
• Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians

  2026cites this paper
• LCF3D: A robust and real-time late-cascade fusion framework for 3D object detection in autonomous driving

  2026influential citation
• Pixel-Perfect Visual Geometry Estimation

  2026cites this paper
• Novel RSS based UGV tracking scheme using coverage area distribution

  2026cites this paper
• LSON-IP: Lightweight Sparse Occupancy Network for Instance Perception

  2026cites this paper
• WHU-PCPR: A cross-platform heterogeneous point cloud dataset for place recognition in complex urban scenes

  2026cites this paper
• Semantic Misalignment in Vision-Language Models under Perceptual Degradation

  2026cites this paper
• Dense Depth Map Estimation Based on Camera–LiDAR Sensor Fusion

  2026cites this paper
• BikeActions: An Open Platform and Benchmark for Cyclist-Centric VRU Action Recognition

  2026cites this paper
• Class debiased teacher for source-free object detection

  2026cites this paper
• Boosting 3-D Point Cloud Registration by Orthogonal Self-Ensemble Learning

  2026cites this paper
• OCC-Exoskeleton: A Plug-and-Play Module to Enhance CNN-Based Occupancy Prediction Networks

  2026cites this paper
• ASCFormer: An Adaptive Structure-Aware Cascaded Transformer for 3D Object Detection

  2026cites this paper
• A PointPillars-based 3D point cloud object detector of USVs for small target detection in dynamic aquatic environments

  2026cites this paper
• Collaborative Sensing and Communication for Intelligent Connected Vehicles: A Comprehensive Survey

  2026cites this paper
• LinkNet3D: An efficient end-to-end network for 3D object detection

  2026cites this paper
• MFFMN: Multi-feature fusion Mamba enhancement network for LiDAR-based 3D object detection

  2026cites this paper
• Collaboratively supervised video instance segmentation: A cost-effective framework with spatio-temporal manipulation

  2026cites this paper
• PCNet3D++: A pillar-based cascaded 3D object detection model with an enhanced 2D backbone

  2026cites this paper
• From Single Perception to Multimodal Collaboration: The Development Path and Innovation Prospects of Vision–Olfactory Fusion: A Review

  2026cites this paper
• Fast and high-Accuracy state estimator for some unknown dynamic objects with a stereo camera in aerial tracking

  2026cites this paper
• SmokeAttack: Physically-based adversarial smoke for LiDAR point cloud detectors

  2026cites this paper
• EvSAM: Segment Anything Model with Event-based Assistance

  2026cites this paper
• Large scale analysis of dataset and simulation biases in SLAM research

  2026cites this paper
• Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising

  2026cites this paper
• An adaptive Laplacian-based smoothing method for LiDAR data processing in space

  2026cites this paper
• Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views

  2026cites this paper
• MoE3D: A Mixture-of-Experts Module for 3D Reconstruction

  2026cites this paper
• 3D object detection based on frustum-fusion for embedded systems

  2026cites this paper
• Finer monocular depth estimation with long range in various driving lighting environments

  2026influential citation
• Robust Occluded Object Detection in Multimodal Autonomous Driving: A Fusion-Aware Learning Framework

  2026cites this paper
• Knowledge graph representation of the mappings between seizure semiology and epileptogenic zones

  2026cites this paper
• An enhanced traffic object detection network based on multi-point attention and sparse feature aggregation

  2026cites this paper
• Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data

  2026cites this paper
• Towards LiDAR point cloud geometry compression using rate-distortion optimization and adaptive quantization for human-machine vision

  2026cites this paper
• A robust multi-sensor fusion model against adversarial patch attack

  2026cites this paper
• Spiking Neural-Invariant Kalman Fusion for Accurate Localization Using Low-Cost IMUs

  2026cites this paper
• Accelerating Outlier-Robust Point Cloud Registration by Known Gravity Directions

  2026cites this paper
• SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddings

  2026cites this paper
• Monocular vision-based 3D ship detection: From image pixels to spatial perception

  2026cites this paper
• NanoSD: Edge Efficient Foundation Model for Real Time Image Restoration

  2026cites this paper
• View refinement net: Pluralistic shape completion

  2026cites this paper
• A Decade of Video Analytics at Edge: Training, Deployment, Orchestration, and Platforms

  2026cites this paper
• A Review: Recent Advancements in Online Private Mode Multiobject Tracking

  2026cites this paper
• Mamba-Stereo: Mamba Regularization for Stereo matching

  2026cites this paper
• USVTrack: A Benchmark for Multi-Object Tracking in Complex Water Surface Scenes

  2026cites this paper
• Context-Guided Multiscale Attention for Real-Time Semantic Segmentation of Road Scene

  2026cites this paper
• A comprehensive survey on image fusion: Which approach fits which need

  2026cites this paper
• From task-specific to foundation models: A paradigm shift in medical vision-language analysis

  2026cites this paper
• COPIC: A Codesigned Accelerator for Efficient Octree-Based Learned Point Cloud Compression at Edge

  2026cites this paper
• A deep learning-assisted model-based tightly coupled visual-inertial method for attitude estimation with visual failure conditions

  2026cites this paper
• Semantic-Aware and Depth-Adaptive LiDAR SLAM With Contextual Loop Closure in Dynamic Environments

  2026cites this paper
• Delving Into the Secrets of BEV 3D Object Detection in Autonomous Driving: A Comprehensive Survey

  2026cites this paper
• A Progressive Multilevel Mixing-based knowledge distillation framework for enhancing three-dimensional object detection on compressed point clouds

  2026cites this paper
• Uncertainty-Aware LiDAR Object Registration Algorithm for Urban Semantic Mapping

  2026cites this paper
• Unsupervised Object Localization driven by self-supervised foundation models: A comprehensive review

  2026cites this paper
• Object-Guided Semi-Supervised Bird’s-Eye View 3D Object Detection With 3D Box Refinement

  2026cites this paper
• UAV-based monocular 3D panoptic mapping for fruit shape completion in orchard

  2026cites this paper
• Time-resolved spray characterization via unified optical flow and binarization technique

  2026cites this paper
• A survey of machine learning-driven task scheduling approaches for multiprocessor systems

  2026cites this paper
• AQUDF: Adaptive frequency annealing with quadratic-enhanced implicit surface reconstruction

  2026cites this paper
• DB-CVF: Dual-Branch Cost Volume Fusion for Multiframe Monocular Depth Estimation in Dynamic Environments

  2026cites this paper
• mmReg: Centimeter-Level and Real-Time mmWave Radar Point Cloud Registration for Multivehicle Sensing

  2026cites this paper
• Enhancing VIO/PPP Navigation Using High-Definition Maps in Complex Urban Environments

  2026cites this paper
• Post-Refining LiDAR Point Cloud Registration via Diffusion-Based Correspondence Refinement

  2026cites this paper
• Attention-integrated one-stage detector with weighted feature fusion for small object detection in aerial images

  2026cites this paper
• FreqBEV-V2I: Frequency-Domain BEV-Enhanced Vehicle-to-Infrastructure Cooperative 3D Detection

  2026influential citation
• Real-time stereo reconstruction and geometric quantification of pavement distress with a variable-baseline platform

  2026cites this paper
• NLSDR-Net: A Lightweight Nonlocal Spatial Disparity Refinement Network for Robust and Real-Time Stereo Matching

  2026cites this paper
• BioGraphLoc: Bio-Inspired Static Structure Graph for Robust LiDAR Global Localization

  2026cites this paper
• SAHA: Supervised Autonomous HArvester for selective forest thinning

  2026cites this paper
• Learnability-Driven Submodular Optimization for Active Roadside 3D Detection

  2026cites this paper
• DST-Calib: A Dual-Path, Self-Supervised, Target-Free LiDAR-Camera Extrinsic Calibration Network

  2026cites this paper
• LabelAny3D: Label Any Object 3D in the Wild

  2026cites this paper
• MLDF-BEV: a multi-layer decoupled fusion networks-based method for 3D object detection in autonomous driving

  2026cites this paper
• Systematic Evaluation of Depth Backbones and Semantic Cues for Monocular Pseudo-LiDAR 3D Detection

  2026cites this paper
• Lunar Rover Cargo Transport: Mission Concept and Field Test

  2026cites this paper
• Cross-dataset late fusion of Camera–LiDAR and radar models for object detection

  2026cites this paper
• UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition

  2026influential citation
• Fusion of multi-scale geometric features and frequency domain decomposition for stereo matching network

  2026cites this paper