GitHub

Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models (ECCV 2024, Oral)

This is the official code for the ECCV 2024 paper "Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models". The format of the dataset is as ...
IEEE

PLPFusion: Plane-Line-Pixel Fully Sparse Fusion for Robust Multi-Modal 3D Object Detection

Abstract: Fully sparse fusion makes an excellent balance between efficiency and accuracy in multi-modal 3D object detection. However, most existing methods focus on foreground objects while ...
GitHub

DDet3D: Embracing 3D Object Detector with Diffusion

This is the official PyTorch implementation of the paper DDet3D: Embracing 3D Object Detector with Diffusion, by Gopi Krishna Erabati and Helder Araujo. Existing approaches rely on heuristic or ...
IEEE

Unsupervised 3D Object Segmentation of Point Clouds by Geometry Consistency

Abstract: In this paper, we study the problem of 3D object segmentation from raw point clouds. Unlike existing methods which usually require a large amount of human annotations for full supervision, ...