PoseCNN | Object Pose Estimation

Object Pose Estimation · 2018 · RSS · CCF Unranked

PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes

Combines semantic segmentation, translation estimation, and rotation regression. It is a representative early deep-learning approach to 6D pose associated with the YCB-Video dataset.

Paper Code

Research area

Object Pose Estimation

Task level

Instance-level

Object setting

Seen objects

Input modalities

RGB-D

Requirements

camera intrinsicsobject maskCAD modeldepth for evaluation/refinement

Full paper metadata Authors, affiliations, research area, datasets, metrics, method tags, and reading status Expand

Authors: Yu Xiang, Tanner Schmidt, Venkatraman Narayanan, Dieter Fox
Affiliations: University of Washington / NVIDIA
Conference / journal: Conference · RSS · CCF Unranked
Research area: Object Pose Estimation
Code availability: Code available
Reading status: Overview:Available Deep Dive:Available
Task setting: Instance-level · Seen objects
Datasets: YCB-Video LINEMOD
Evaluation metrics: ADD-S 2D Projection
Method tags: 2D–3D Correspondences Dense Correspondences & Coordinate Fields Multi-object Pose Estimation Instance-level Pose Estimation Absolute Pose Estimation
Requirements: camera intrinsicsobject maskCAD modeldepth for evaluation/refinement

Reading Notes

Overview / Deep Dive

Available src/paper-notes/posecnn/coarse.md

Paper overview notes

Quickly assess the paper's scope, problem setting, core method, experimental findings, and whether to read it in depth.

Reading notes have not yet been added. Markdown notes placed at the path above will appear here once available.

Planned note structure

01 Basic information
02 Positioning in one sentence
03 Method inputs and outputs
04 Problem setting
05 Core motivation
06 Method overview
07 Experimental overview
08 Strengths and limitations
09 Research takeaways

Related papers

2026 · CVPR

3PT

3PT unifies detection, segmentation, and 6-DoF pose with two Transformers for 2D / 3D object-centric understanding. Continuous refinement of object representations and rendered-feature alignment support zero-shot cross-object perception on BOP-H3, BOP-Industrial, and BOP-Classic.

2026 · AAAI

6DAttack

Studies backdoor attacks on PnP-based and end-to-end 6-DoF pose pipelines. Structurally 3D triggers and modified pose labels are injected into training data so that models behave normally on clean inputs but produce controlled incorrect poses when triggered.

2026 · ICRA

Active Tactile Exploration

A violation-implicit loss incorporates physical-constraint violations into joint estimation of freely moving unknown convex rigid-body trajectories and cuboid / 20-vertex polytope shapes. Observed / Fisher information at a local MLE estimates EIG to select the next touch. In simulation, the EIG strategy yields stable errors below 4 mm after 5 cuboid actions; real Trifinger results at step 5 substantially outperform random selection. Convex geometry, local optima, multiple initializations, and tactile / proprioceptive errors limit the method.