Hansheng Chen 陈涵晟

Publications
3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation

Hansheng Chen, Bokui Shen, Yulin Liu, Ruoxi Shi, Linqi Zhou, Connor Z. Lin, Jiayuan Gu, Hao Su, Gordon Wetzstein, Leonidas Guibas
arXiv, 2024

3D-Adapter enables high-quality 3D generation using a 3D feedback module attached to a base image diffusion model for enhanced geometry consistency.

project page Demo arXiv GitHub
MVEdit: Generic 3D Diffusion Adapter Using Controlled Multi-View Editing

Hansheng Chen, Ruoxi Shi, Yulin Liu, Bokui Shen, Jiayuan Gu, Gordon Wetzstein, Hao Su, Leonidas Guibas
arXiv, 2024

MVEdit is a training-free 3D-Adapter that enables 3D generation/editing using off-the-shelf 2D Stable Diffusion models. An updated version of MVEdit has been merged into the 3D-Adapter project.

project page Demo arXiv GitHub
GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

Yinghao Xu, Zifan Shi, Wang Yifan, Hansheng Chen, Ceyuan Yang, Sida Peng, Yujun Shen, Gordon Wetzstein
ECCV, 2024

GRM is a sparse-view feed-forward 3D Gaussian splatting reconstruction model with high efficiency (~0.1s). When combined with multi-view image diffusion, GRM can generate high-quality 3D objects from texts or images.

project page Demo arXiv GitHub
One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion

Minghua Liu*, Ruoxi Shi*, Linghao Chen*, Zhuoyang Zhang*, Chao Xu*, Xinyue Wei, Hansheng Chen, Chong Zeng, Jiayuan Gu, Hao Su
CVPR, 2024

Combining multiview diffusion and multiview-conditioned 3D diffusion models, One-2-3-45++ is capable of transforming a single RGB image of any object into a high-fidelity textured mesh in under one minute.

project page Demo arXiv GitHub
Zero123++: A Single Image to Consistent Multi-view Diffusion Base Model

Ruoxi Shi, Hansheng Chen, Zhuoyang Zhang, Minghua Liu, Chao Xu, Xinyue Wei, Linghao Chen, Chong Zeng, Hao Su
Technical report, 2023

Zero123++ transforms a single RGB image of any object into high-quality multiview images with superior 3D consistency, serving as a strong base model for image-to-3D generative tasks.

Demo arXiv GitHub
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction

Hansheng Chen, Jiatao Gu, Anpei Chen, Wei Tian, Zhuowen Tu, Lingjie Liu, Hao Su
ICCV, 2023

With 3D diffusion models and NeRFs trained in a single stage, SSDNeRF learns powerful 3D generative prior from multi-view images, which can be exploited for unconditional generation and image-based 3D reconstruction.

project page arXiv GitHub
EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Hansheng Chen, Pichao Wang, Fan Wang, Wei Tian, Lu Xiong, Hao Li
CVPR, 2022 (Best Student Paper)

We present a probabilistic PnP layer for end-to-end 6DoF pose learning. The layer outputs the pose distribution with differentiable probability density, so that the 2D-3D correspondences can be learned flexibly by backpropagating the pose loss.

arXiv GitHub video
EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Hansheng Chen, Wei Tian, Pichao Wang, Fan Wang, Lu Xiong, Hao Li
TPAMI, 2024

The updated paper features improved models with better results on both the LineMOD and nuScenes benchmark. Morever, we have added more discussions on the loss functions, which are supported by rigorous ablation studies.

arXiv GitHub
MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation

Hansheng Chen, Yuyao Huang, Wei Tian, Zhong Gao, Lu Xiong
CVPR, 2021

We present a novel 3D object detection framework based on dense 2D-3D correspondences. An uncertainty-aware reprojection loss is proposed to learn the 3D coordinates without prior knowledge of the object geometry.

arXiv GitHub
SPFCN: Select and Prune the Fully Convolutional Networks for Real-time Parking Slot Detection

Zhuoping Yu, Zhong Gao, Hansheng Chen, Yuyao Huang
IEEE Intelligent Vehicles Symposium (IV), 2020

A real time parking slot detection model that runs 30 FPS on a 2.3 GHz CPU core, yielding corner localization error of 1.51±2.14 cm (std. err.) and slot detection accuracy of 98%.

arXiv GitHub