LIME: Learning Intent-aware Camera Motion from Egocentric Video
Autonomous robots often need to move their camera before they can act: to inspect an object, reveal an occluded region, or obtain a view that responds to a user's intent. While vision-language navigation translates instructions to base motion and vision-language-action policies map instructions to manipulation actions, language-conditioned camera motion remains comparatively underexplored as a first-class action. We formulate language-conditioned camera motion generation: given a current RGB observation and a free-form natural-language intent, predict a relative target camera pose for the next
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorBoyang Sun →
LIME: Learning Intent-aware Camera Motion from Egocentric Video
- Linked via arxiv authorJiajie Li →
LIME: Learning Intent-aware Camera Motion from Egocentric Video
- Linked via arxiv authorYung-Hsu Yang →
LIME: Learning Intent-aware Camera Motion from Egocentric Video
- Linked via arxiv authorChenyangguang Zhang →
LIME: Learning Intent-aware Camera Motion from Egocentric Video
- Linked via arxiv authorTim Engelbracht →
LIME: Learning Intent-aware Camera Motion from Egocentric Video
- Linked via arxiv authorSunghwan Hong →
LIME: Learning Intent-aware Camera Motion from Egocentric Video
- Linked via arxiv authorCesar Cadena →
LIME: Learning Intent-aware Camera Motion from Egocentric Video
- Linked via arxiv authorMarc Pollefeys →
LIME: Learning Intent-aware Camera Motion from Egocentric Video
- Linked via arxiv authorHermann Blum →
LIME: Learning Intent-aware Camera Motion from Egocentric Video