Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection (ECCV 2026) - GitHub Repository
By
Ubin108
Summary
This is a GitHub repository page for Group3D, an academic research project accepted at ECCV 2026. The project introduces a method called "MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection," developed by researchers at Sungkyunkwan University and Yonsei University. The page primarily contains installation instructions for setting up the codebase, including cloning the repository and installing dependencies via conda and pip. The content is essentially a code repository README with minimal explanatory text about the actual research.
Source
Twitter / XGroup3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection (ECCV 2026) - GitHub Repositorygithub.comKey quotes
· 4 pulledGroup3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection
Youbin Kim · Jinho Park · Hogun Park · Eunbyung Park
1 Sungkyunkwan University 2 Yonsei University
ECCV 2026
You might also wanna read
LL3M: Large Language Models for 3D Asset Creation in Blender
LL3M (Large Language 3D Modelers) is a system developed by the University of Chicago that employs large language models to generate Python c
Mesh-LLM: Distributed LLM Inference System Using llama.cpp Across Multiple Machines
Mesh-LLM is a reference implementation that enables distributed inference of large language models across multiple machines by compiling lla
github.com·3mo ago
Ultralytics YOLO26: A Unified Real-Time Vision Model Family with NMS-Free Inference and Advanced Training Pipeline
Ultralytics YOLO26 is a new family of real-time vision models that addresses key limitations of prior YOLO detectors. It introduces a dual-h
arxiv.org·11d ago
Fast-dLLM: Training-Free Acceleration Method for Diffusion Language Models Using KV Cache and Parallel Decoding
Researchers introduce Fast-dLLM, a training-free acceleration method for diffusion-based large language models that addresses their slower i
arxiv.org·8mo ago
SemDLM+: Improving Diffusion Language Models by Balancing Bias and Variance in Transition Kernel Design
This paper analyzes sensitivity in Diffusion Language Models (DLMs) through generalization error analysis, identifying three critical factor
arxiv.org·17d ago
ShapeLib: Using LLMs to Design Programmatic 3D Shape Abstraction Libraries
ShapeLib is a novel method that leverages Large Language Models (LLMs) to design libraries of programmatic 3D shape abstractions. The system
arxiv.org·1mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.