ccloy Profile Banner
Chen Change Loy Profile
Chen Change Loy

@ccloy

Followers
3K
Following
2K
Statuses
901

President's Chair Professor @NTUsg Director of @MMLabNTU Computer vision and deep learning

Singapore
Joined November 2010
Don't wanna be here? Send us removal request.
@ccloy
Chen Change Loy
@ccloy
7 months
We turned our method, rejected by CVPR and ECCV, into the iOS app "Cutcha". EdgeSAM, our fast Segment Anything Model, runs at over 30 FPS on an iPhone 14. Enjoy intuitive one-touch object selection and precise editing—all processed locally on your device. No cloud needed! Download now on the App Store! 📸✨ Kudos to our in-house development team Han Soong and Voon Hueh #Cutcha #EdgeSAM #PhotoEditing #iOSApp
Tweet media one
8
25
212
@ccloy
Chen Change Loy
@ccloy
4 days
RT @ShangchenZhou: 🔥Introducing #𝐌𝐚𝐭𝐀𝐧𝐲𝐨𝐧𝐞 for human video matting!🔥 🤡 Fast video matting with customizable target 🤡 Stable human tracking…
0
95
0
@ccloy
Chen Change Loy
@ccloy
15 days
RT @KangLiao929: Happy to share that our work "Denoising as Adaptation" has been accepted to #ICLR2025! Huge thanks to @ccloy and all colla…
0
14
0
@ccloy
Chen Change Loy
@ccloy
15 days
RT @BoLi68567011: I think the image metaphor of DeepSeek is incorrect. Recently, there has been a lot of discussion about DeepSeek. Many p…
0
19
0
@ccloy
Chen Change Loy
@ccloy
21 days
RT @liuziwei7: 🔥Unbounded 4D City Generation🔥 #CityDreamer4D is a generative model of unbounded 4D cities that decouples static and dynami…
0
61
0
@ccloy
Chen Change Loy
@ccloy
1 month
@DMBTrivia @chaseleantj Thanks! We are trying.
0
0
3
@ccloy
Chen Change Loy
@ccloy
2 months
RT @zeqi_xiao: Introducing 💡Trajectory Attention for Fine-grained Video Motion Control💡. By augmenting attention along predefined trajector…
0
10
0
@ccloy
Chen Change Loy
@ccloy
2 months
RT @dreamingtulpa: Omegance can control detail levels in diffusion-based synthesis using a single parameter, ω (uwu???) Guess we don't nee…
0
16
0
@ccloy
Chen Change Loy
@ccloy
2 months
RT @XingangP: Introducing 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐀𝐧𝐲𝐭𝐡𝐢𝐧𝐠, a new 3D generative model with two key properties: - A structured point-cloud latent space ena…
0
50
0
@ccloy
Chen Change Loy
@ccloy
2 months
RT @_akhaliq: Omegance A Single Parameter for Various Granularities in Diffusion-Based Synthesis
0
9
0
@ccloy
Chen Change Loy
@ccloy
2 months
RT @XingangP: Introducing 𝐒𝐀𝐑𝟑𝐃, which tokenizes 3D objects into multiscale tokens and generates 3D objects by autoregressive next-scale pr…
0
49
0
@ccloy
Chen Change Loy
@ccloy
3 months
RT @XingangP: Can we drag 3D objects with large structure changes, like what we can do with DragGAN? Our work 🤏𝐌𝐕𝐃𝐫𝐚𝐠𝟑𝐃🐦 makes this possib…
0
28
0
@ccloy
Chen Change Loy
@ccloy
5 months
RT @caizhongang: 🚀 Announcing GTA-Human II for expressive human pose & shape estimation! Compared to its predecessor, this latest game-pla…
0
12
0
@ccloy
Chen Change Loy
@ccloy
5 months
RT @caizhongang: 🚀 HuMMan-MoGen is here! 🚀 HuMMan v1.0: Motion Generation Subset features 112,112 fine-grained temporal (by stage) and spat…
0
17
0
@ccloy
Chen Change Loy
@ccloy
5 months
RT @caizhongang: HuMMan v1.0: 3D Vision Subset (HuMMan-Point) has just been released! ✅ RGB-D @ 30 FPS ✅ Captured with Kinect & iPhone ✅ 34…
0
16
0
@ccloy
Chen Change Loy
@ccloy
6 months
@AlbertBoyangLi Congrats, Albert!
1
0
5
@ccloy
Chen Change Loy
@ccloy
6 months
Check out our ProPainter here
@AIWarper
A.I.Warper
@AIWarper
6 months
Remove the soccer ball and you are left with an oddly funny video 😂 Fully automated object removal with SAM V2 + ProPainter
0
4
25
@ccloy
Chen Change Loy
@ccloy
6 months
Like this work!
@_FelixHeide_
Felix Heide
@_FelixHeide_
6 months
Split-Aperture 2-in-1 Cameras at #SIGGRAPH2024 for single-shot HDR, hyperspectral, and depth imaging! By splitting the camera aperture and using a dual-pixel sensor, we show that it is possible to capture an optically coded and conventional image simultaneously without increasing the camera size! This makes the conditional reconstruction problem so much easier! Project: Super fun project with Zheng Shi, @_ilya_c , Mario Bijelic, Geoffroi Côté, Jiwoon Yeom, Qiang Fu, Hadi Amata, Wolfgang Heidrich.
0
0
2
@ccloy
Chen Change Loy
@ccloy
7 months
The training code is now available
0
0
0
@ccloy
Chen Change Loy
@ccloy
7 months
@Neiluss_ We haven't had a plan yet
1
0
1
@ccloy
Chen Change Loy
@ccloy
7 months
Excited to share that our survey paper "Transformer-Based Visual Segmentation: A Survey" is now accepted by TPAMI! 📝 🔍 Highlights: 1️⃣ Unlike previous surveys, we categorize transformer-based methods from a technical perspective. 2️⃣ We explore methods for mainstream tasks with DETR-like meta-architecture and related directions by tasks. 3️⃣ We re-benchmark representative works on image semantic & panoptic segmentation datasets. Paper: GitHub repo: Hard work from Xiangtai Li @xtl994 , Henghui Ding @HenghuiDing , Haobo Yuan @HarborYuan , Wenwei Zhang @wenweiz97 and other co-authors.
Tweet media one
0
9
59