, top-down and isometric views).
World coordinates replace learned features for game model control
ActionRoPE directly encodes camera displacement into positional embeddings, enabling geometrically precise motion in planar-camera game world models.
Chinese Tech
Zhiyang Deng · Yuzhe Wu · Zijun Lin · Yeying Jin
Tencent · National University of Singapore · Nanyang Technological University
Research Digest··3 min read
The authors propose ActionRoPE, a parameter-free interface that converts action-driven camera displacement into world-coordinate rotary positions for planar-camera game world models.
§