홈 › Papers

SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation

2026-03-22 · Wen Jiang, Kangyao Huang, Li Wang, Wang Xu, Wei Fan, Jinyuan Liu, Shaoyu Liu, Hanfang Liang, Hongwei Duan, Bin Xu, Xiangyang Ji, Huaping Liu arxiv

UAVs play an important role in applications such as autonomous exploration, disaster response, and infrastructure inspection. However, UAV VLN in complex 3D environments remains challenging. A key difficulty is the structural representation mismatch between 2D visual perception and the 3D trajectory decision space, which limits spatial reasoning. To this end, we propose SpatialFly, a geometry-guided spatial representation framework for UAV VLN. Operating on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D adaptive representation mechanism. Specifically, the geometric prior injection module injects global structural cues into 2D semantic tokens to provide scene-level geometric guidance. The geometry-aware reparameterization module then uses geometry-conditioned cross-modal attention and gated residual fusion to adaptively reparameterize the visual tokens. Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments, reducing NE by 4.03m and improving SR by 1.27% over the strongest baseline on the unseen Full split. Additional trajectory-level analysis shows that SpatialFly produces trajectories with better path alignment and smoother, more stable motion.

📄 PDF Abstract BibTeX arXiv:2603.21046

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction Spatial Reasoning

Implicit Reparameterization Gradients

2018-05-22 · NeurIPS 2018 12 · Michael Figurnov, Shakir Mohamed, andriy mnih

By providing a simple and efficient way of computing low-variance gradients of continuous random variables, the reparameterization trick has become the technique of choice for training a variety of latent variable models…

DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization

2026-05-09 · Ao Li, Xiaoning Liu, Sheng Li, Yapeng Du 외 arxiv

All-in-one image restoration aims to handle diverse degradations within a single model. However, existing methods often suffer from three key limitations: 1) per-input computational overhead from dynamic degradation esti…

Image Restoration

Encoding Semantic Priors into the Weights of Implicit Neural Representation

2024-06-06 · Zhicheng Cai, Qiu Shen

Implicit neural representation (INR) has recently emerged as a promising paradigm for signal representations, which takes coordinates as inputs and generates corresponding signal values. Since these coordinates contain n…

CT Reconstruction MRI Reconstruction Novel View Synthesis

Explicit Preference Optimization: No Need for an Implicit Reward Model

2025-06-09 · Xiangkun Hu, Lemin Kong, Tong He, David Wipf

The generated responses of large language models (LLMs) are often fine-tuned to human preferences through a process called reinforcement learning from human feedback (RLHF). As RLHF relies on a challenging training seque…

Geometry-guided Emotion Modulation for Controllable and Photorealistic Emotional Talking Face Generation

2026-08-01 · Chenggong Hu, Shaoyin Ma, Yi Wang, Li Sun 외 arxiv

Audio-driven emotional talking face generation aims to synthesize realistic videos with expressive facial dynamics. However, existing methods struggle to balance controllability and visual fidelity. Although implicit rep…

Talking Face Generation Continuous Control