LocateAnyMesh: Grounding 3D Mesh Queries in 2D Images with Vision-Language Models
cs.CV, cs.AI
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/om-ai-lab/VLX-Seek
Terminology
Sources
- SAM 3: Segment Anything with Concepts
- Detect Anything via Next Point Prediction
- Aligning Text, Images, and 3D Structure Token-by-Token
- CAD-Prompted SAM3: Geometry-Conditioned Instance Segmentation for Industrial Objects
- LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs