Zhenjun Zhao (@zhenjun_zhao)
2025-12-30 | โค๏ธ 127 | ๐ 19
KV-Tracker: Real-Time Pose Tracking with Transformers
@marwan_ptr, @alzugarayign, @makezur, @XinKong_IC, @AjdDavison
tl;dr: KV-cache is underlying implicit scene representation
https://arxiv.org/abs/2512.22581 https://x.com/zhenjun_zhao/status/2006024295214907556/photo/1
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
๐ Related
- v-dpm-4d-video-reconstruction-with-dynamic-point-maps
- chain-of-view-makes-vision-language-models-move-through-a
- what-if-sim-and-reality-were-one-this-system-keeps-them-in
- objsplat-geometry-aware-gaussian-surfels-for-active-object
- gen3r-3d-scene-generation-meets-feed-forward-reconstruction