Blog

Research updates, product announcements, and industry insights from Visincept.

Latest Article

DINO-XSeek

DINO-XSeek is a referring object detection model based on a multimodal large language model, designed to precisely locate objects based on user-input natural language descriptions.

Qing JiangFebruary 28, 2025

Previous Articles

3D 重建的终局是开放世界自由 | IDEA 张磊、光影焕像谭平团队发布 3D 场景生成框架 SceneMaker
3D 重建的终局是开放世界自由 | IDEA 张磊、光影焕像谭平团队发布 3D 场景生成框架 SceneMaker
视启未来January 25, 2026
打破 3D 感知瓶颈：OVSeg3R 如何推动开集 3D 实例分割应用落地
打破 3D 感知瓶颈：OVSeg3R 如何推动开集 3D 实例分割应用落地
视启未来January 21, 2026
ScanNet200 新纪录！张磊团队发布 SegDINO3D：用 2D 模型能力大幅提升 3D 实例分割性能
ScanNet200 新纪录！张磊团队发布 SegDINO3D：用 2D 模型能力大幅提升 3D 实例分割性能
视启未来December 31, 2025
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
Tianhe RenNovember 20, 2024
Grounding DINO 1.6
Grounding DINO 1.6
Tianhe RenJuly 19, 2024
Grounding DINO 1.5 Pro
Grounding DINO 1.5 Pro
Tianhe RenNovember 16, 2024
Grounding DINO 1.5 Edge
Grounding DINO 1.5 Edge
Wenlong LiuNovember 16, 2024
T-Rex2: Towards Generic Object Detection via Visual-Text Prompt Synergy
T-Rex2: Towards Generic Object Detection via Visual-Text Prompt Synergy
Qing JiangMarch 22, 2024
Grounding DINO
Grounding DINO
Shilong LiuApril 12, 2023
DINO: Advancing Object Detection with Transformers
DINO: Advancing Object Detection with Transformers
Hao ZhangJuly 12, 2022