Welcome! I am a research scientist at Snap Research working with Kfir Aberman on Personalized AI Generation. I graduated as a Ph.D. in Computer Science at KAUST, under the supervision of Prof. Bernard Ghanem.
Prior to that, I received my B.Eng degree with the highest undergraduate honor from Xi'an Jiaotong University (XJTU).
My primary research interests lie in creative vision and generative modeling.
My representative work includes PointNeXt (NeurIPS), ASSANet (NeurIPS Spotlight), DeepGCNs (T-PAMI), Magic123 (ICLR) and Omni-ID.
If you are interested in working in generative models with us, please drop me a message through guocheng.qian [at] outlook.com
Ph.D. in CS
KAUST , 2019 - 2023
B.Eng in ME
XJTU , 2014 - 2018
Exchange Student
HKUST , 2017 Spring
Check my full publication at Google Scholar
WonderLand is a video-latent based approach for single-image 3D reconstruction in large-scale scenes.
Omni-ID is a novel facial representation tailored for generative tasks, encoding identity features from unstructured images into a fixed-size representation that captures diverse expressions and poses.
AC3D studies when and how you should condition camera signals into a video diffusion model for a better camera control and a higher video quality.
AToM trains a single text-to-mesh model on many prompts using 2D diffusion without 3D supervision, yileds high-quality textured meshes under a second, and generalizes to unseen prompts.
Magic123 is a coarse-to-fine image-to-3D pipeline that produces high-quality high-resolution 3D content from a single unposed image by the guidance of both 2D and 3D priors.
We propose a state-of-the-art Standard Transformer model for point cloud understanding and find that image pretraining helps point cloud tasks.
ZeroSeg trains open-vocabulary zero-shot semantic segmentation models using only CLIP Vision Encoder
PointNeXt boosts the performance of PointNet++ to the state-of-the-art level with improved training and scaling strategies.
ASSANet makes PointNet++ faster and more accurate.