works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.CV2026

AdaAnchor4D: Anchor-Conditioned Spatiotemporal Feature Aggregation for Monocular UAV 4D Reconstruction

Peiyi Xu, Junpeng Zhang, Guanbin Li +6

The paper introduces AdaAnchor4D, a method that uses adaptive anchor-based feature aggregation to improve monocular UAV video reconstruction of dynamic urban scenes, reducing artif…

cs.CV2026

SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions

Jie Feng, Jiawei Shen, Junjia Huang +4

3D indoor scene generation conditioned on short textual descriptions provides a promising avenue for interactive 3D environment construction without the need for labor-intensive la…

cs.CV2026

Are VLMs Lost Between Sky and Space? LinkSBench for UAV-Satellite Dynamic Cross-View Spatial Intelligence

Dian Liu, Jie Feng, Di Li +4

Synergistic spatial intelligence between UAVs and satellites is indispensable for emergency response and security operations, as it uniquely integrates macro-scale global coverage…

cs.CV2026

Back2Color: Domain-Adaptive Synthetic-to-Real Monocular Depth Estimation for Dynamic Traffic Scenes

Yufan Zhu, Chongzhi Ran, Mingtao Feng +3

Accurate monocular depth estimation is a fundamental component of vision-based perception systems in intelligent transportation applications. Despite recent progress, unsupervised…

cs.CV2025

SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting

Di Li, Jie Feng, Jiahao Chen +5

3D affordance reasoning, the task of associating human instructions with the functional regions of 3D objects, is a critical capability for embodied agents. Current methods based o…

cs.CV2025

Learning Coherent Matrixized Representation in Latent Space for Volumetric 4D Generation

Qitong Yang, Mingtao Feng, Zijie Wu +4

Directly learning to model 4D content, including shape, color, and motion, is challenging. Existing methods rely on pose priors for motion control, resulting in limited motion dive…