DeepIM: Deep Iterative Matching for 6D Pose Estimation
Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the observed image can produce accurate results. In this work, we propose a novel deep neural network for 6D pose matching named DeepIM. Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using an untangled representation of 3D location and 3D orientation and an iterative training process. Experiments on two commonly used benchmarks for 6D pose estimation demonstrate that DeepIM achieves large improvements over state-of-the-art methods. We furthermore show that DeepIM is able to match previously unseen objects.
Code (2)
Tasks
6D Pose Estimation6D Pose Estimation using RGBPose EstimationRobot ManipulationSimilar Papers 제목 키워드 기반
Generalized Machine Learning for Fast Calibration of Agent-Based Epidemic Models
Agent-based models (ABMs) are widely used to study infectious disease dynamics, but their calibration is often computationally intensive, limiting their applicability in time-sensitive public health settings. We propose …
Learning Passage Impacts for Inverted Indexes
Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized languag…
Information RetrievalLanguage ModelingLanguage ModellingRe-Ranking+1DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual s…
Temporal SequencesImage RetrievalDeep Interaction Machine: A Simple but Effective Model for High-order Feature Interactions
Click-Through Rate (CTR) prediction is a crucial task for various online applications, such as recommendation and online advertising. The task of CTR prediction is to predict the probability of users' clicking behaviors,…
Click-Through Rate PredictionFeature EngineeringDeep Interaction Machine: A Simple but Effective Model for High-order Feature Interactions
Click-Through Rate (CTR) prediction is a crucial task for various online applications, such as recommendation and online advertising. The task of CTR prediction is to predict the probability of users' clicking behaviors,…
Click-Through Rate PredictionFeature Engineering