Deying Li

Dust to Tower: Prior-Driven Coarse-to-Fine Photo-Realistic Scene Reconstruction From Sparse Uncalibrated Images

Xudong Cai, Yongcai Wang, Zhaoxin Fan, Haoran Deng et autres

Photo-realistic scene reconstruction from sparse-view, uncalibrated images is highly required in practice. Although some successes have been made, existing methods are either Sparse-View but require accurate camera parameters (i.e., intrinsic and extrinsic), or SfM-free but need densely captured images. This paper proposes …

cn (code pays fourni par la source)

MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming

Shuo Wang, Yongcai Wang, Zhaoxin Fan, Yucheng Wang et autres

Vision-Language Navigation (VLN) tasks often leverage panoramic RGB and depth inputs to provide rich spatial cues for action planning, but these sensors can be costly or less accessible in real-world deployments. Recent approaches based on Vision-Language Action (VLA) models achieve strong results …

cn, us, sg (code pays fourni par la source)

Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction

Xudong Cai, Shuo Wang, Peng Wang, Yongcai Wang et autres

Reconstructing dense geometry for dynamic scenes from a monocular video is a critical yet challenging task. Recent memory-based methods enable efficient online reconstruction, but they fundamentally suffer from a Memory Demand Dilemma: The memory representation faces an inherent conflict between the long-term …

cn (code pays fourni par la source)

MapDream: Task-Driven Map Learning for Vision-Language Navigation

Guoxin Lian, Shuo Wang, Yucheng Wang, Yongcai Wang et autres

Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. However, most existing approaches rely on hand-crafted maps constructed independently of the navigation policy. We argue that …

MapDream: Task-Driven Map Learning for Vision-Language Navigation

Guoxin Lian, Shuo Wang, Yucheng Wang, Yongcai Wang et autres

Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. However, most existing approaches rely on hand-crafted maps constructed independently of the navigation policy. We argue that …