CinemaTraj: Language-Grounded Camera Trajectory Planning

Loading video

Reframes camera trajectory planning as language-grounded spatial reasoning, equipping an LLM agent with a structured 3D scene graph to decompose prompts into trajectories

相机轨迹规划语言推理 LLM agent 3D场景图 spatial reasoning CinemaTraj perception Twitter

Category: perception

Author: @ai_bites

Date: 2026-08-01T00:00:00

Duration: 12.533s

Source: https://x.com/ai_bites/status/2083448414210015468

DART turns SAM3 into a real-time open-vocabulary detector at 55.8 AP on COCO

DART turns SAM3 into a real-time open-vocabulary detector at 55.8 AP on COCO

@rsasaki0109 · 89 views · 2026-08-29

目标检测open-vocabulary detectionSAM3

Monocular-camera basketball motion analysis system

Monocular-camera basketball motion analysis system

@tokufxug · 9 views · 2026-08-19

篮球动作解析单目视觉

Inside SuperMap: Persistent 3D Object Identities

Inside SuperMap: Persistent 3D Object Identities

@robotsdigest · 10 views · 2026-08-16

SLAMSuperMapSuperOdometry

SuperMap Turns SLAM into Persistent 4D Spatial Memory

SuperMap Turns SLAM into Persistent 4D Spatial Memory

@robotsdigest · 9 views · 2026-08-16

SLAMSuperMap空间记忆

DeWorldSG: Probabilistic 3D Gaussian Scene Graph Generation (ECCV 2026)

DeWorldSG: Probabilistic 3D Gaussian Scene Graph Generation (ECCV 2026)

@tokufxug · 7 views · 2026-08-14

3D场景图Scene Graph3DGS

DeWorldSG: depth-aware 3D scene graph generation

DeWorldSG: depth-aware 3D scene graph generation

@rsasaki0109 · 5 views · 2026-08-13

3D场景图scene graphDeWorldSG