Mengwei Ren (@mengweir) / X

Mengwei Ren

71 posts

Mengwei Ren

@mengweir

Building @PhotaLabs | ex Research Scientist @Adobe. CS PhD from NYU | Generative Models

New York

Joined January 2017

Pinned
Mengwei Ren
@mengweir
Mar 26
Photography is deeply personal. It’s about people, relationships, and moments that matter — shaping how we remember the world and the people around us. So excited to finally share what we’ve been working on - a personalized photo generation and editing model designed for your
5.7K
Mengwei Ren
@mengweir
Mar 2, 2024
Glad to share that our project Relightful Harmonization: Lighting-aware portrait background replacement has been accepted to #CVPR2024. 🧵 Project page: mengweiren.com/research/relig… Preprint: arxiv.org/abs/2312.06886
27K
Mengwei Ren
@mengweir
Oct 16, 2024
So much fun at #AdobeMAX sneak! As a researcher, this is so far the biggest stage I have ever stepped on. Turns out it’s easier to interact with 10k+ audiences than with 1 for an introvert :p Grateful for all the applause, energy, and suports!
Howard Pinsky
@Pinsky
Oct 16, 2024
Excuse me what?! #ProjectPerfectBlend needs to come to Photoshop, like, now! 🤯
00:00
23K
Mengwei Ren
@mengweir
Dec 12, 2023
While everyone is enjoying New Orleans… Glad to share that I passed my Ph.D thesis defense! Deeply grateful for the support and inspiration I've received from everyone who has been a part of this incredible journey. 🌟
00:00
7K
Mengwei Ren
@mengweir
Jul 15, 2023
Glad to share that our project during my internship was accepted to #ICCV2023. Thanks the amazing LUMA team for a wonderful internship experience 🫶Hope to see you in-person soon! @2ptmvd @docmilanfar
Peyman Milanfar
@docmilanfar
Jul 14, 2023
Replying to @docmilanfar
Multiscale Structure Guided Diffusion for Image Deblurring DPMs for restoration work well on benchmarks but not real images. We fix this with a guided formulation that leads to significantly better visual quality on out of domain images. arxiv.org/abs/2212.01789 #ICCV2023 (3/3)
12K
Mengwei Ren
@mengweir
Dec 11, 2023
If you are at #NeurIPS23, welcome to stop by our poster and @Georgey52775077 will present our work on keypoint-augmented SSL! Unfortunately I won't be there in-person this time, but feel free to DM & connect :) time/loc: Dec13 afternoon, #811 arxiv: arxiv.org/abs/2310.01680
3K
Mengwei Ren
@mengweir
Oct 5, 2023
Thanks @docmilanfar ! And kudos @CSProfKGD for the great photo 😊
Peyman Milanfar
@docmilanfar
Oct 5, 2023
Great job @mengweir on your paper and poster - your hard work really paid off - Congrats! + thanks to the very capable social media chair @CSProfKGD for the great photo
3K
Mengwei Ren
@mengweir
Jun 17, 2024
At @CVPR until the 21st, feel free to DM, swing by and meet up :) Poster: June 19 afternoon Arch 4A-E Poster #161
Mengwei Ren
@mengweir
Mar 2, 2024
Glad to share that our project Relightful Harmonization: Lighting-aware portrait background replacement has been accepted to #CVPR2024. 🧵 Project page: mengweiren.com/research/relig… Preprint: arxiv.org/abs/2312.06886
2.2K
Mengwei Ren
@mengweir
Mar 2, 2024
Replying to @mengweir
[5/5, n=5] This project is done during my internship last summer at @Adobe @AdobeResearch collaborating with my amazing mentors/collaborators Wei, JaeShin, Zhixin, Jianming, HyunJoon, He @zhanghesprinter, to name a few. Thanks everyone for making this happen :)
GIF
4.8K
Mengwei Ren
@mengweir
Oct 11, 2024
I am presenting at #AdobeMAX next week! Get a sneak peak to our latest research on image composition and relighting on Oct15th at MAX sneak session (5.30 to 7 pm EST). Online registration (free): max.adobe.com/max-online/
00:00
2.5K
Mengwei Ren
@mengweir
Sep 15, 2022
Happy to announce that our work on spatiotemporal representation learning in image-to-image architectures was just accepted to #NeurIPS! Preprint can be accessed here: arxiv.org/abs/2206.04281. 🧵
arxiv.org
Local Spatiotemporal Representation Learning for...
Recent self-supervised advances in medical computer vision exploit global and local anatomical self-similarity for pretraining prior to downstream tasks such as segmentation. However, current...
Mengwei Ren
@mengweir
Nov 28, 2022
Coming to New Orleans? Let’s grab a coffee ☕️
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
Mengwei Ren
@mengweir
Mar 2, 2024
Replying to @mengweir
[3/n] We introduce a lighting-aware diffusion model designed to seamlessly harmonize sophisticated lighting effect for the foreground portrait using any background image. We develop a three-stage training pipeline.
694
Mengwei Ren
@mengweir
Oct 16, 2024
Replying to @GoldieChan
Thank you!! 😊
106