AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight

Yunze Man, Shihao Wang, Guowen Zhang, Johan Bjorck, Liang-Yan Gui, Jim Fan, Jan Kautz, Yu-Xiong Wang, Zhiding Yu

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
serialize objects near-to-far instead of random (ablation)LocateAnything3D · Omni3D OUTAP3D outdoor: 17.5 -> 33.1Improved
serialize objects near-to-far instead of left-to-right (ablation)LocateAnything3D · Omni3D OUTAP3D outdoor: 30.6 -> 33.1Improved
add 2D box step before 3D (Chain-of-Sight) instead of direct 3D (ablation)LocateAnything3D · Omni3D OUTAP3D outdoor: 22.7 -> 33.1Improved
emit 2D before 3D rather than 3D-then-2D (ablation)LocateAnything3D · Omni3D OUTAP3D outdoor: 26.2 -> 33.1Improved
decode center-size-rotation instead of rotation-size-center (ablation)LocateAnything3D · Omni3D OUTAP3D outdoor: 28.8 -> 33.1Improved
decode size before rotation (CSR vs CRS) (ablation)LocateAnything3D · Omni3D OUTAP3D outdoor: 32.9 -> 33.1Improved
predict 2D and 3D jointly end-to-end vs external 2D detector boxesLocateAnything3D · Omni3D novel categories (zero-shot)AP3D kitti: 25.73 -> 25.87No clear effect
predict 2D and 3D jointly vs external Grounding-DINO 2D boxesLocateAnything3D · Omni3D novel categories (zero-shot)AP3D SUN-RGBD: 21.07 -> 26.33Improved
LocateAnything3D vs DetAny3D given ground-truth 2D boxesLocateAnything3D · Omni3D (full, indoor+outdoor)AP3D: 34.38 -> 38.90Improved
LocateAnything3D vs DetAny3D with GT 2D boxes on nuScenesLocateAnything3D · Omni3D OUTAP3D nuScenes: 36.7 -> 33.9Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy