method · first seen 15 Oct 2026
camera pose conditioning
Injecting estimated camera poses and 3D geometry into model attention to inform spatial understanding.
Mentions per week
PapersCodeDiscussion
Earliest sources
- DK-VLM: Geometry as Position for Spatial Reasoning in Vision-Language ModelsPapers · 15 Oct 2026 · Han Su, Meng Tian, Tianyu Huang, Mingyu Gao, Lennox Wei, Dongxu Li, Jianhua Han,…
Latest sources
- DK-VLM: Geometry as Position for Spatial Reasoning in Vision-Language ModelsPapers · 15 Oct 2026 · Han Su, Meng Tian, Tianyu Huang, Mingyu Gao, Lennox Wei, Dongxu Li, Jianhua Han,…