Xiaohang Zhan

AI Researcher

[Xiaohang Zhan @xiaohangzhan]

Our paper LaRender received full marks at ICCV 2025 and was selected as oral! This paper enables control of occlusion relationships among objects and visual effects in a training-free manner for diffusion-based image generation. Project page: https://t.co/XzjMZuJ4a4

[Fangfu Liu @fangfu0830]

🔥Revolutionize Video Generation with Test-Time Scaling!🔥

Big thanks to @_akhaliq for sharing our work! Video-T1's code is now fully open-sourced!🎉Contributions and feedback are welcome!���
Code: https://t.co/otJC0Z8ACF
Project page: https://t.co/otJC0Z8ACF

[Xiaohang Zhan @xiaohangzhan]

@yshan2u @_akhaliq

[Xiaohang Zhan @xiaohangzhan]

I am always excited to do some interesting researches. Our paper "Programmable Motion Generation", accepted at CVPR 2024 (highlight), is released now. I will be in front of the poster. Welcome to drop by.
Paper: https://t.co/Iu0x1E46yi
Project page: https://t.co/Tw22TuQuRf

[Xiaohang Zhan @xiaohangzhan]

Many thanks to Hanchao Liu, Taijiang Mu, @yshan2u !

[camenduru @camenduru]

HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting 🔥 Colab 🥳

Thanks to Xian Liu ❤ @xiaohangzhan ❤ Jiaxiang Tang ❤ Ying Shan ❤ Gang Zeng ❤ @lindahua ❤ Xihui Liu ❤ @liuziwei7 ❤

🌐page: https://t.co/E6lDvyoLOt
📄paper: https://t.co/Z0fFmOxF5g
🧬code: https://t.co/3UO3bXRH5V
🦒colab by https://t.co/uUxzMCZb53: please try it 🐣 https://t.co/M8WR0B066C

[AK @_akhaliq]

Unsupervised Object-Level Representation Learning from Scene Images
pdf: https://t.co/jYccf0MAvu
project page: https://t.co/U1pZ5NtIbe

improves the performance of SSL on scene images,
even surpassing supervised ImageNet pre-training on several downstream tasks

[AK @_akhaliq]

Do 2D GANs know 3D shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs
pdf: https://t.co/KmazfjXV0C
abs: https://t.co/hSCfpbsO91

[Bo Dai @doubledaibo]

Oral at #ECCV2020 ! Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation https://t.co/Q7cIfFgro3
1/3

[DeepAI @DeepAI]

Online Deep Clustering for Unsupervised Representation Learning
https://t.co/KRDJORDNyM
by @xiaohangzhan et al. including @liuziwei7, @ccloy
#Classifier #ComputerScience

[Xiaohang Zhan @xiaohangzhan]

I will answer any questions about OpenSelfSup in CVPR online session in 12:00am ~ 2:00am PDT (poster 2.2 second showing), welcome! https://t.co/3Ou5N6xjjB

[Ziwei Liu @liuziwei7]

We are releasing, #OpenSelfSup, an open-source library for self-supervised learning:

https://t.co/7d0crGEpyM

- *All methods in one repository*, supporting PIRL, MoCo, SimCLR, etc.
- *All benchmarks in one repository*.
- *Efficiency*, supporting multi-GPU distributed training.

[Xiaohang Zhan @xiaohangzhan]

Thanks. Glad to hear that so many people like this work.

[Hendrik Schilling @hendrikrabbitai]

Very cool approach by @xiaohangzhan et al. performing "Self-Supervised Scene De-Occlusion". Principled formulation and neat solution on how to create de-occlusion training data from instance segmentation labels.
#hendrikspapers #CVPR2020 #CVPR

[Shalini De Mello @shalinidemello]

Introducing "Self-supervised Single-view 3D Reconstruction via Semantic Consistency" -- without 3D shape, keypoints, viewpoint, or templates! @XueT_Li , @SifeiL, @jampani_varun, Ming-Hsuan Yang, @jankautz, @NVIDIAAI.

Paper: https://t.co/4nYY9ncM6C
Video: https://t.co/QleDG6KYzt

[Ziwei Liu @liuziwei7]

Our #CVPR2020 **oral** paper "Self-Supervised Scene De-occlusion":

Paper: https://t.co/GEwMiRRWm4
Code: https://t.co/M78ezgRl5q
Demo: https://t.co/Nzhk0u5n5e

- A self-supervised framework that can recover occluded objects & their spatial orders from a single RGB image.

[Xiaohang Zhan @xiaohangzhan]

Thanks @GokuMohandas
Demo video: https://t.co/iIyGGPq4u7 Code: https://t.co/qphhCoUtzk