Roni Sengupta
@SenguptRoni • 2,612 subscribers
Asst. Professor @unccs, Prev. postdoc @uwcse (UW), Ph.D. @umiacs (Univ. of Maryland). Computer Vision & Graphics (she/her)
Videos
🚀 Excited to attend my first #NeurIPS2025 and present our lighting-aware SLAM method, NFL-BA! 🔗 🔦 Why this matters: Traditional Bundle Adjustment (BA) in SLAM assumes static lighting, but many real scenarios—endoscopy, search & rescue, subterranean robotics—use co-located light + camera, creating dynamic, near-field lighting that breaks these assumptions. ✨ What we introduce: Near-Field Lighting Bundle Adjustment Loss (NFL-BA) — a formulation that explicitly models near-field illumination inside the BA objective, allowing SLAM systems to jointly reason about geometry, appearance, and lighting. 📈 Results: Modeling lighting directly leads to ~38% improvement in mapping & tracking across dynamic-lighting sequences in both endoscopy and indoor scenes. 🧩 Plug-and-play: NFL-BA integrates seamlessly into existing neural rendering–based SLAM pipelines, using both implicit (NeRF-style) or explicit (3DGS) scene representations. 🌟 If you’re interested in SLAM, neural rendering, or illumination modeling, come check it out on Friday's poster session, 11-2pm, #4407.
Roni Sengupta21,130 görüntüleme • 6 ay önce
SLAM algorithms struggle on endoscopy videos - specularity, textureless, & dynamic near-field lighting. We introduce a Near-Field Light Bundle Adjst. loss (NFL-BA): improves performance of SOTA SLAM, e.g. MonoGS (⬆️35% in tracking, ⬆️48% in mapping). See
Roni Sengupta19,140 görüntüleme • 1 yıl önce
📢New research from our group “Personalized Video Relighting with an At-Home Light Stage” (1/3) We show how to leverage screen lighting as an 'at-home Light Stage' and develop a personalized relighting model. We can now replace your background and relight your faces to match it!
Roni Sengupta25,221 görüntüleme • 2 yıl önce
Daha fazla içerik yok.