3 citations · 6 across the 9 of their papers we have counts for
5 papers · 1 filter
SpatialSkill: Self-Evolving Skills for Cross-View Spatial Reasoning
Ruifan Zuo, Guocheng Hu, Wanshui Gan +3
Cross-view spatial reasoning requires a model to align different viewpoints into a coherent spatial representation, yet this ability remains challenging for vision-language models…
OccAnyScene: Towards Unified Indoor-Outdoor 3D Occupancy Prediction
Junjie Liu, Wanshui Gan, Zitong Dai +6
3D occupancy prediction is fundamental to scene understanding, yet existing 3D semantic occupancy methods are typically specialized to fixed scene types and occupancy protocols. We…
MegaParts: Scaling Part-Aware 3D Object Generation to 300 Parts via Token-Efficient Autoregressive Modeling
Manwen Liao, Xinyu Lian, Jian Mao +11
Part-aware 3D object generation is essential for graphics applications such as controllable modeling, editing, and articulation, where objects are represented as coherent assemblie…
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Yixuan Yang, Zhen Luo, Wanshui Gan +5
Designing realistic and functional 3D indoor rooms is essential for a wide range of applications, including interior design, virtual reality, gaming, and embodied AI. While recent…
Enhancing 3D LiDAR Segmentation by Shaping Dense and Accurate 2D Semantic Predictions
Xiaoyu Dong, Tiankui Xian, Wanshui Gan +1
Semantic segmentation of 3D LiDAR point clouds is important in urban remote sensing for understanding real-world street environments. This task, by projecting LiDAR point clouds an…