Shangchen Zhou
@ShangchenZhou
Followers
1K
Following
926
Media
9
Statuses
106
Research Assistant Professor at NTU @MMLabNTU - Computer Vision
Singapore
Joined June 2016
We welcome submissions to the MIPI Workshop!🤗.Website: .Deadline: Jul 08, 2025.
🚨 Call for Papers – Deadline Approaching!.📸 MIPI Workshop @ ICCV 2025.📅 Oct 20, 2025 | 📍 Honolulu, Hawai‘i. Topics: low-level vision, enhancement, editing, efficient AI, camera systems & more!. Don’t miss your chance to present—submit now:.🔗
2
1
4
RT @GROS17121524: 🔥Streaming-based 3D/4D Foundation Model🔥. We present STream3R, which reformulates dense 3D/4D reconstruction into a seque….
huggingface.co
0
16
0
RT @camenduru: 🔍 SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training 🎥 Jupyter Notebook 🥳. Thanks to @Iceclearwjy ❤….
0
19
0
RT @Gradio: 🔥🆕 ObjectClear is an object removal model that can jointly eliminate the target object and its associated effects (shadow etc)….
0
28
0
RT @camenduru: 👁️ ObjectClear: Complete Object Removal via Object-Effect Attention 🧹 Jupyter Notebook 🥳. Thanks to Jixin Zhao ❤ @Shangchen….
0
23
0
Just tried generating a Cyberpunk-style website for #ObjectClear with #Anycoder (by @_akhaliq). Looks pretty cool!. Anycoder Space:
0
2
14
With #ObjectClear, you can now remove any objects, along with their shadows and reflections, from your images in just a few clicks or strokes!. 👉Try our demo (click version): Big thanks to @_akhaliq @AdinaYakup!
5
19
118
RT @soumikRakshit96: ✨ CVPR 2025 highlight #3 ---.MatAnyone: Stable Video Matting with Consistent Memory Propagation. MatAnyone is a robust….
0
22
0
Cool project: creating an LLM using just prompts.
Customizing Your LLMs in seconds using prompts🥳!.Excited to share our latest work with @HPCAILab, @VITAGroupUT, @k_schuerholt, @YangYou1991, @mmbronstein, @damianborth : Drag-and-Drop LLMs(DnD). 2 features: tuning-free, comparable or even better than full-shot tuning.(🧵1/8)
0
1
3
🔥Introducing #ObjectClear: remove objects & their effects in one shot! Check out more results here:
ObjectClear can remove objects from images while also getting rid of shadows and reflections
0
3
12
RT @XingangP: The Bokeh Effect is so important in photography, yet existing text2image diffusion models do not support controling bokeh str….
0
10
0
RT @TheYihangLuo: 💥 Consistent Multi-View Diffusion for 3D Enhancement 💥. Introducing our work #3DEnhancer @CVPR: a multi-view diffusion mo….
0
10
0
RT @peiqing001: Happy to share our 𝙈𝙖𝙩𝘼𝙣𝙮𝙤𝙣𝙚 is accepted to #CVPR2025! 🥳. 🤡 Fast video matting with customizable target.🤡 Stable human trac….
github.com
[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation - pq-yang/MatAnyone
0
24
0
Our #MatAnyone demo is now live! 🎉 Try it out here: .Thanks @_akhaliq !.
huggingface.co
this looks insane, MatAnyone . Stable Video Matting with Consistent Memory Propagation
0
1
8
🔥Introducing #𝐌𝐚𝐭𝐀𝐧𝐲𝐨𝐧𝐞 for human video matting!🔥. 🤡 Fast video matting with customizable target.🤡 Stable human tracking.🤡 Fine-grained matting details. - Paper: - Project: - Code (soon):
17
98
651