Tianyu (Steve) Wang (@visionsteve) 's Twitter Profile
Tianyu (Steve) Wang

@visionsteve

Research Scientist @AdobeResearch | Ph.D. @ CUHK | Prev. Research Intern @AdobeResearch | Photographer | Opinions are my own

ID: 1195855307794255872

linkhttp://stevewongv.github.io calendar_today17-11-2019 00:05:14

210 Tweet

628 Followers

430 Following

Shaoteng Liu (@shaotengliu) 's Twitter Profile Photo

We propose GenProp✨, a generative video propagation framework, which can seamlessly propagate any first frame edit through the video. 🧵(1/n) - Arxiv: arxiv.org/abs/2412.19761 - Project Page: genprop.github.io - Video: youtube.com/watch?v=GC8qfW…

Yijun Li (@leexiaoju) 's Twitter Profile Photo

Here comes our Transpixar tech, generating video frames and their corresponding alpha channel together for the first time, making the content immediately ready for composition. No green screen anymore! 🤓 Super pround of our intern Luozhou and thanks for other collaborators!

Tianyu (Steve) Wang (@visionsteve) 's Twitter Profile Photo

3/3 papers are accepted #CVPR2025 Thanks ACs, PCs, reviewers and my team! Two intern projects I co-led last summer and my previous intern project finally completed 🤣

#CVPR2025 (@cvpr) 's Twitter Profile Photo

#CVPR2025 Area Chairs (ACs) identified a number of highly irresponsible reviewers, those who either abandoned the review process entirely or submitted egregiously low-quality reviews, including some generated by large language models (LLMs). 1/2

Xin Yu (Andy) (@andy_yx27) 's Twitter Profile Photo

🚀 I am very glad to share that our work #ObjectMover is accepted by #CVPR2025! 🎉 We introduce an image editing model that enables realistic object movement/removal/insertion by leveraging a video diffusion model. Project Page: xinyu-andy.github.io/ObjMover/ How?👇

Kai Zhang (@kaizhang9546) 's Twitter Profile Photo

Excited to finally share our unnamed blog capturing the incredible efforts we put together last summer! research.adobe.com/news/adobe-res…

Mihir Prabhudesai (@mihirp98) 's Twitter Profile Photo

1/ Happy to share UniDisc - Unified Multimodal Discrete Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in

Sam Altman (@sama) 's Twitter Profile Photo

thrilled to be partnering with jony, imo the greatest designer in the world. excited to try to create a new generation of AI-powered computers.

Tianyu (Steve) Wang (@visionsteve) 's Twitter Profile Photo

We will organize HiGen @ ICCV 2025 in Honolulu! Join us to explore human-interactive generation with top speakers from Adobe, Stanford, CMU, and more. Submit by June 30 for a chance to win $800! #ICCV2025 #ICCVworkshop #HiGen

We will organize HiGen @ ICCV 2025 in Honolulu! Join us to explore human-interactive generation with top speakers from Adobe, Stanford, CMU, and more. Submit by June 30 for a chance to win $800! #ICCV2025 #ICCVworkshop #HiGen
Adobe Research (@adoberesearch) 's Twitter Profile Photo

Adobe Labs releases an experimental digital photography app Project Indigo (adobe.ly/43VWAV7) to showcase breakthrough innovations, including reflection removal, which is being published at CVPR this week. Check out this blog: adobe.ly/4kFNFOJ

Adobe Labs releases an experimental digital photography app Project Indigo (adobe.ly/43VWAV7) to showcase breakthrough innovations, including reflection removal, which is being published at CVPR this week. Check out this blog: adobe.ly/4kFNFOJ