Computer Vision – ECCV 2022

Lane Detection Transformer Based on Multi-Frame Horizontal andVertical Attention and Visual Transformer Module.- ProposalContrast: Unsupervised Pre-training for LiDAR-Based 3D Object Detection.- PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map.- Master of All: Simultaneous Generalization of Urban-Scene Segmentation to All Adverse Weather Conditions.- LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds.- Visual Cross-View Metric Localization with Dense Uncertainty Estimates.- V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer.- DevNet: Self-Supervised Monocular Depth Learning via Density Volume Construction.- Action-Based Contrastive Learning for Trajectory Prediction.- Radatron: Accurate Detection Using Multi-Resolution Cascaded MIMO Radar.- LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection.- Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks.- FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-World Point Clouds.- SpatialDETR: Robust Scalable Transformer-Based 3D Object Detection from Multi-View Camera Images with Global Cross-Sensor Attention.- Pixel-Wise Energy-Biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes.- Rethinking Closed-Loop Training for Autonomous Driving.- SLiDE: Self-Supervised LiDAR De-Snowing through Reconstruction Difficulty.- Generative Meta-Adversarial Network for Unseen Object Navigation.- Object Manipulation via Visual Target Localization.- MoDA: Map Style Transfer for Self-Supervised Domain Adaptation of Embodied Agents.- Housekeep: Tidying Virtual Households Using Commonsense Reasoning.- Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects.- Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction.- OPD: Single-View 3D Openable Part Detection.- AirDet: Few-Shot Detection without Fine-Tuning for Autonomous Exploration.- TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance.- StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning.- TIDEE: Tidying Up Novel Rooms Using Visuo-Semantic Commonsense Priors.- Learning Efficient Multi-agent Cooperative Visual Exploration.- Zero-Shot Category-Level Object Pose Estimation.- Sim-to-Real 6D Object Pose Estimation via Iterative Self-Training for Robotic Bin Picking.- Active Audio-Visual Separation of Dynamic Sound Sources.- DexMV: Imitation Learning for Dexterous Manipulation from Human Videos.- Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments.- Style-Agnostic Reinforcement Learning.- Self-Supervised Interactive Object Segmentation through a Singulation-and-Grasping Approach.- Learning from Unlabeled 3D Environmentsfor Vision-and-Language Navigation.- BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking.- FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion.- Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning.- Video Dialog As Conversation about Objects Living in Space-Time.