EPO is a trackless, edge-map-alignment framework that refines pose estimates from 3D foundation models and matches or exceeds bundle-adjustment performance with substantially lower runtime and memory use.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
PoseShield learns a neural collision field directly in SMPL pose space with Eikonal regularization to correct self-collisions post-hoc in human pose estimation and motion generation, achieving 95.8% success on a new benchmark.
GazeVLA pretrains on large human egocentric datasets to capture gaze-based intention, then finetunes on limited robot data with chain-of-thought reasoning to achieve better robotic manipulation performance than baselines.
X-Imitator is a bidirectional action-pose interaction framework for spatial-aware imitation learning that outperforms vanilla policies and explicit pose guidance on 24 simulated and 3 real-world robotic tasks.
citing papers explorer
-
EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization
EPO is a trackless, edge-map-alignment framework that refines pose estimates from 3D foundation models and matches or exceeds bundle-adjustment performance with substantially lower runtime and memory use.
-
PoseShield: Neural Collision Fields for Human Self-Collision Resolution
PoseShield learns a neural collision field directly in SMPL pose space with Eikonal regularization to correct self-collisions post-hoc in human pose estimation and motion generation, achieving 95.8% success on a new benchmark.
-
GazeVLA: Learning Human Intention for Robotic Manipulation
GazeVLA pretrains on large human egocentric datasets to capture gaze-based intention, then finetunes on limited robot data with chain-of-thought reasoning to achieve better robotic manipulation performance than baselines.
-
X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction
X-Imitator is a bidirectional action-pose interaction framework for spatial-aware imitation learning that outperforms vanilla policies and explicit pose guidance on 24 simulated and 3 real-world robotic tasks.