Roni Sengupta
@SenguptRoni
Asst. Professor @unccs, Prev. postdoc @uwcse (UW), Ph.D. @umiacs (Univ. of Maryland). Computer Vision & Graphics (she/her)
Some good news amidst a lot of bad news over last one month! ScribbleLight will be presented at CVPR! See y’all at Nashville!
💡Introducing ScribbleLight, a generative model that can relight an image with simple scribbles - making it easier for virtual staging and interior design of homes. Lead by Jun, collabs with @anand_bhattad, P. Peers, @Annie_N_Wang. @unccs 👉 Project: chedgekorea.github.io/ScribbleLight/
Welcome to @unccs! So excited to have another addition to our Computer Vision faculty! Looking forward to exciting collaborations 🎉
💡Introducing ScribbleLight, a generative model that can relight an image with simple scribbles - making it easier for virtual staging and interior design of homes. Lead by Jun, collabs with @anand_bhattad, P. Peers, @Annie_N_Wang. @unccs 👉 Project: chedgekorea.github.io/ScribbleLight/
The UniLight Workshop at @ICCVConference 2025 focuses on the evaluation of lighting-related tasks such as relighting, composition, and harmonization. Don’t miss our fantastic speaker line-up! unilight-workshop.github.io/unilight2025/
#CVPR2025 is a wrap! Amazing contributions on lighting-related tasks this year. Now it’s time to look ahead to #ICCV2025 in beautiful Hawai’i. Let’s keep the momentum going and join us to explore and discuss how to evaluate lighting across diverse tasks!
📣 Reminder: Full paper deadline for the AI for Visual Arts (AI4VA) Workshop @ICCVConference #ICCV2025 is June 19! 🎨 AI + creativity, culture & storytelling 📝 Accepted papers published in ICCV proceedings 🔗 Submit: openreview.net/group?id=thecv… 🌐 Info: sites.google.com/view/ai4vaiccv…
🎨 The AI for Visual Arts (AI4VA) Workshop is back for its 2nd edition at #ICCV2025 in Honolulu, HI, USA! 📢 Now accepting full papers (archival) & extended abstracts (non-archival). 🌐 Topics & CFP: sites.google.com/view/ai4vaiccv… 📝 Submit: openreview.net/group?id=thecv… @ICCVConference
Had a great time at #CVPR2025 — from organizing Broadening Participation to the AC workshop, WiCV keynotes, and presenting our ScribbleLight poster! But the best part was reconnecting with old friends and making new ones and getting inspired from each other. See you in Denver!
Join us for afternoon session poster #26 to talk about lighting and generative models!
💡Introducing ScribbleLight, a generative model that can relight an image with simple scribbles - making it easier for virtual staging and interior design of homes. Lead by Jun, collabs with @anand_bhattad, P. Peers, @Annie_N_Wang. @unccs 👉 Project: chedgekorea.github.io/ScribbleLight/
🔥 Next up at #WiCV @CVPR Prof. Roni Sengupta discussing "Learning to See the Light: Foundation Models for Lighting-Aware Perception." Enjoyable talk on how lighting impacts computer vision models! 💡⚡️ #CVPR2025 #WomenInCV
Thank you for the invite and excited to talk about Lighting in Computer Vision💡
🌟 We’re thrilled to welcome Professor @SenguptRoni as a keynote speaker at #WiCV2025 at @CVPR! 📢 Don’t miss her talk: “Learning to See the Light: Foundation Models for Lighting-Aware Perception” 🔗 sites.google.com/view/wicv-cvpr… 📅 June 12th | Nashville, TN, USA
Tomorrow (Jun 12) we’re organizing the first Inductive Bias in 3D Generation workshop at #CVPR2025! Join us starting at 1 PM in Davidson C3. We have a great lineup of talks around 3D priors and generation. Hope to see you there! @CVPR Schedule: ind3dworkshop.github.io/cvpr2025/#sche…
Top minds. Deep ideas. 🎯 Inductive Bias in 3D Generation 🗓️ June 12 — Day 2 of CVPR. Be there!
Had a fun time attending @unccs Computer Vision past and present meetup at #CVPR2025 , missing a lot of folks though 😌
So excited to finally make this happen! Looking forward to having you at UNC Avi!
Big news! 🎉 I’m joining UNC-Chapel Hill as an Assistant Professor in Computer Science starting next year! Before that, I’ll be spending time @OpenAI working on LLM privacy. @unccs @uncnlp
Why is shape from shading hard?
Kusursuz burun için makyaj hileleri.
Celebrating the achievements of your first set of students (PhD and MS) is always special 😍 will miss them 🥹
🔍 3D is not just pixels—we care about geometry, physics, topology, and functions. But how to balance these inductive biases with scalable learning? 👀 Join us at Ind3D workshop @CVPR (June 12, afternoon) for discussions on the future of 3D models! 🌐 ind3dworkshop.github.io/cvpr2025
Happy to see this accepted in #SIGGRAPH2025 in the Journal Track! Congratulations @QiLuchao for the hard work and the amazing results! Wish I could travel to Vancouver 😢
Thank you @_akhaliq for posting our work! 🔥Excited to share our recent work “MyTimeMachine: Personalized Facial Age Transformation”. 🔥 🤔 How can we simulate a person’s aging across their entire lifespan—for instance, Al Pacino transforming from age 0 to 100? 😇 By…
Happy to share our latest work: IntrinsiX 🥳 peter-kocsis.github.io/IntrinsiX/ We generate intrinsic components directly from text! Using SDS, our model can generate full room-scale PBR textures, ready for photo-realistic rendering. Big shout-out to @LukasHollein and @MattNiessner!
📢 IntrinsiX: High-Quality PBR Generation using Image Priors 📢 From text input, we generate renderable PBR maps! Next to editable image generation, our predictions can be distilled into room-scale scenes using SDS for large-scale PBR texture generation. We first train…
[1/8] Is scene understanding solved? We can label pixels and detect objects with high accuracy. But does that mean we truly understand scenes? Super excited to share our new paper and a new task in computer vision: Visual Jenga! 📄arxiv.org/abs/2503.21770…