Research map / Detection and segmentation / Open-set and few-shot detection
Promptable 3-D Object Localization with Latent Diffusion Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a promptable diffusion-based approach for 3-D object localization that operates in latent space, moving beyond the standard noise-to-box formulation of diffusion detectors.
Problem
Accurate identification and localization of objects in 3-D scenes for 3-D scene understanding; diffusion models' potential for 2-D and 3-D object detection remains underexplored, and existing diffusion detectors use a noise-to-box process.
Approach
Formulates 3-D object localization as a promptable latent diffusion process rather than the existing noise-to-box formulation; the abstract is truncated so the exact mechanism is not fully stated.
Closest papers by meaning
- DiffuBox: Refining 3D Object Detection with Point Diffusion (NeurIPS 2024 · similarity 0.89)
- PromptDet: A Lightweight 3D Object Detection Framework with LiDAR Prompts (AAAI 2025 · similarity 0.88)
- 3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features (CVPR 2024 · similarity 0.88)
- Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection (CVPR 2025 · similarity 0.88)
- Prompt3D: Random Prompt Assisted Weakly-Supervised 3D Object Detection (CVPR 2024 · similarity 0.87)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.87)
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.