16 papers
Unordered Landmark Visual Navigation
Hao Ren, Junzhe Zhu, Yihan Li +8
Image-goal navigation is a fundamental capability for embodied AI, yet its practical deployment is strained by strong prior assumptions. Existing methods predominantly rely on temp…
PanoWorld: Real-World Panoramic Generation
Haoyuan Li, Dizhe Zhang, Yuemei Zhou +7
In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotation-equivariant property of omnidirectional representations, whe…
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
Weijian Chen, Weibo Yao, Yuhang Zhang +7
Scaling 3D Gaussian Splatting (3DGS) to large outdoor scenes is costly in both data acquisition and computation. Adopting panoramic images with equirectangular projection (ERP) can…
Fisher-Preserving Guidance: Training-Free Manifold Constraints for Safe Diffusion Control
Hao Ren, Zetong Bi, Yiming Zeng +5
Diffusion models are effective for waypoint prediction in visual navigation, but standard sampling and test time guidance can produce unreliable or inefficient trajectories when up…
STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation
Hao Ren, Zetong Bi, Yiming Zeng +3
Visual navigation requires the robot to reach a specified goal such as an image, based on a sequence of first-person visual observations. While recent learning-based approaches hav…
Fly360: Omnidirectional Obstacle Avoidance within Drone View
Xiangkai Zhang, Dizhe Zhang, WenZhuo Cao +5
Obstacle avoidance in unmanned aerial vehicles (UAVs), as a fundamental capability, has gained increasing attention with the growing focus on spatial intelligence. However, current…