9 papers
AdaAnchor4D: Anchor-Conditioned Spatiotemporal Feature Aggregation for Monocular UAV 4D Reconstruction
Peiyi Xu, Junpeng Zhang, Guanbin Li +6
Monocular UAV videos provide valuable observations for dynamic reconstruction of complex urban scenes. However, such scenes exhibit pronounced spatiotemporal heterogeneity: differe…
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…
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…
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…
Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution
Shuchen Lin, Mingtao Feng, Weisheng Dong +4
Real-world image super-resolution (Real-SR) is a challenging problem due to the complex degradation patterns in low-resolution images. Unlike approaches that assume a broadly encom…
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…
3D Object Detection from Point Cloud via Voting Step Diffusion
Haoran Hou, Mingtao Feng, Zijie Wu +4
3D object detection is a fundamental task in scene understanding. Numerous research efforts have been dedicated to better incorporate Hough voting into the 3D object detection pipe…
External Knowledge Enhanced 3D Scene Generation from Sketch
Zijie Wu, Mingtao Feng, Yaonan Wang +4
Generating realistic 3D scenes is challenging due to the complexity of room layouts and object geometries.We propose a sketch based knowledge enhanced diffusion architecture (SEK)…
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…