5 papers
SpaceVista: All-Scale Visual Spatial Reasoning from mm to km
Peiwen Sun, Shiqiang Lang, Dongming Wu +8
With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications su…
One Walk is All You Need: Data-Efficient 3D RF Scene Reconstruction with Human Movements
Yiheng Bian, Zechen Li, Lanqing Yang +8
Reconstructing 3D Radiance Field (RF) scenes through opaque obstacles is a long-standing goal, yet it is fundamentally constrained by a laborious data acquisition process requiring…
Reflective VLM Planning for Dual-Arm Desktop Cleaning: Bridging Open-Vocabulary Perception and Precise Manipulation
Yufan Liu, Yi Wu, Gweneth Ge +2
Desktop cleaning demands open-vocabulary recognition and precise manipulation for heterogeneous debris. We propose a hierarchical framework integrating reflective Vision-Language M…
Building Real-time Awareness of Out-of-distribution in Trajectory Prediction for Autonomous Vehicles
Tongfe Guo, Taposh Banerjee, Rui Liu +1
Accurate trajectory prediction is essential for the safe operation of autonomous vehicles in real-world environments. Even well-trained machine learning models may produce unreliab…
Enhancing Image Matting in Real-World Scenes with Mask-Guided Iterative Refinement
Rui Liu
Real-world image matting is essential for applications in content creation and augmented reality. However, it remains challenging due to the complex nature of scenes and the scarci…