Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction.
Anil ArmaganGuillermo Garcia-HernandoSeungryul BaekShreyas HampaliMahdi RadZhaohui ZhangShipeng XieMingxiu ChenBoshen ZhangFu XiongYang XiaoZhiguo CaoJunsong YuanPengfei RenWeiting HuangHaifeng SunMarek HrúzJakub KanisZdenek KrnoulQingfu WanShile LiLinlin YangDongheui LeeAngela YaoWeiguo ZhouSijia MeiYunhui LiuAdrian SpurrUmar IqbalPavlo MolchanovPhilippe WeinzaepfelRomain BrégierGrégory RogezVincent LepetitTae-Kyun KimPublished in: CoRR (2020)
Keyphrases
- d objects
- real objects
- visual objects
- object model
- rotationally symmetric
- object shapes
- object shape
- multiple objects
- data objects
- recognizing objects
- viewpoint
- three dimensional objects
- individual objects
- similar objects
- object segmentation
- object classes
- moving objects
- bounding box
- hand pose
- transparent objects
- object contours
- object level
- object class
- shape descriptors
- geometric models
- complex scenes
- object features
- human hand
- target object
- object manipulation
- previously unseen
- real world objects
- polyhedral objects
- complex shapes
- object recognition
- object models
- line drawings
- deformable objects
- human computer interaction
- partial occlusion
- geometric shapes
- human body
- boundary points
- spatial relations
- spatial relationships
- object representation
- multi view
- object parts
- surface patches
- physical objects
- pose estimation
- digital objects
- light source
- training examples
- training set
- geometrical properties
- articulated objects
- object tracking
- planar objects
- complex objects
- shape analysis
- position and orientation
- lighting conditions
- range data
- shape matching
- image sequences