Netflix Fellow, Content Production Research Governor, TV Academy Sci Tech Peer Group Adjunct Research Professor, USC ICT VFX Branch, Academy of Motion Pictures
Hollywood, CA
Joined June 2009
- Tweets358
- Following500
- Followers7.6K
- Likes1.7K
Paul Debevec retweeted
Whenever I see a decorative mirror ball, I think about the old-school OpenGL GL_SPHERE_MAP texgen option, and light probes for realistic lighting of synthetic renderings for merging with photos.
Long before cube maps were an option, sphere maps allowed a form of shiny surface rendering, but only from a limited viewpoint — you couldn’t walk all the way around a shiny object.
For light probes, you could take multiple photos with different exposure times to capture a true many-orders-of-magnitude high dynamic range composite image for realistic image based lighting of everything from direct sunlight to subtle shadowed region indirect lighting.
Congratulations to this year's Engineering, Science, and Technology Emmy Award winners! Awards to be bestowed in Los Angeles October 14th :-)
Full winners list at:
televisionacademy.com/news/f…
@TelevisionAcad @TheEmmys
Excited to be speaking at @mundosdigitales in A Coruna, Spain next week on "Image-Based Lighting: Past, Present and Future" mundosdigitales.org/en/event…
Paul Debevec retweeted
📢 @eyelinestudios and @netflix latest research, 🌟Go-with-the-Track🌟, has been accepted to #SIGGRAPH2026.
We propose a video generation framework that jointly conditions on multiple reference images and reference-anchored point tracks, enabling a range of content creation applications within a unified model:
• Motion-preserving video restylization using multiple reference images;
• Mesh- or keypoint-driven compositing and stylization;
• Camera motion control for both static and dynamic scenes using multiple reference images captured from different view-points and time steps.
✊Congrats to the team: @Koichi_N_, @yash2kant, Zhizheng Liu, @RyanBurgert, @Yuancheng_Xu0, @kuanhenglin, Emmett Steven, @JulienPhilip2, @maleewahaha, Andrea Vedaldi, @debfx, @realNingYu
📰 Paper: arxiv.org/pdf/2606.20891
🌐 Project: eyeline-labs.github.io/Go-wi…
⌨️ Code: github.com/Eyeline-Labs/Go-w…
*** This work is part of the ongoing research and development at @eyelinestudios and @netflix, and we look forward to seeing its techniques and workflows adopted in future productions.
Happy to present "Lighting in Motion" at #CVPR, trained to predict the HDRI map for image-based lighting from anywhere in an LDR image or video. Used for CGI or to drive @eyelinestudios's Light Dome LED stage with lighting from generated backgrounds. eyeline-labs.github.io/LiMo/
Happy to join @jon_barron in congratulating @BenMildenhall and @_pratul_ for their ACM Grace Hopper Award recognizing Neural Radiance Fields -- NeRF's -- which in 2020 dramatically advanced the process of modeling and rendering 3D scenes from photographs.
Congrats @BenMildenhall and @_pratul_! ACM gives Grace Hopper Awards to under-35-year-olds for *one specific thing*, here it's NeRF.
Past winners include Donald Knuth (for "The Art of Computer Programming"), Steve Wozniak (for Apple), and @martin_casado (for SDN). Good company!
Thanks @mikeseymour and @FXGuide for a fun podcast on HDRI lighting and the future of visual effects 🌞💡🎥 fxguide.com/fxpodcasts/paul-… #hdri #visualeffects #scitech
The future of greenscreen? Our @VFXSociety fireside chat with Niko from @CorridorDigital on "Getting to the Matte of It: CorridorKey and the Future of Keying" youtu.be/zwIjc42Tybc?si=YLqI… via @YouTube supported by @eyelinestudios
Excited to be interviewing Niko Pueringer from @CorridorDigital about their CorridorKey greenscreen model tomorrow for the @VFXSociety ... sign up for the 3pm PDT webinar here: us02web.zoom.us/webinar/regi…
Incredibly honored to receive an Academy Award for the VFX technique of High Dynamic Range Image-Based Lighting at @TheAcademy's Sci-Tech Awards this week - thanks to all who made this possible! Video and speech: youtu.be/vO2_rRrA1qQ?si=-PxE…
The @TheAcademy Sci-Tech Awards are tomorrow night, and @CGinLA covers some of the honorees including HDR Image-Based Lighting ! substack.com/home/post/p-194…
Paul Debevec retweeted
📢 Happening in 1h! @Yuancheng_Xu0 and @debfx will be presenting 📷Virtually Being📷@SIGGRAPHAsia 2025 🗓️today (Thur, Dec 18) 11:01-11:12am HKST at📍Meeting Room S423+S424, Level 4 of #HongKong Convention and Exhibition Centre.
👋 To continue our research momentum, @eyelinestudios Labs is hiring research interns. We publish and open-source, aiming to raise the bar together on next-gen AI filmmaking tools.
Spring'26: jobs.lever.co/Eyeline/4eded8…
Summer'26: jobs.lever.co/Eyeline/85f377…
#hiring #internship #AI #AIResearch #MachineLearning #AIGC #GenAI #VideoGeneration
🔊#SIGGRAPHAsia2025 acceptance: ⚡Virtually Being⚡achieves multi-view character consistent, 3D camera controllable video generation finetuned on 4D Gaussian Splatting and relightable video samples.
✊Kudos to the teamwork led by our past intern and current researcher @Yuancheng_Xu0 at @eyelinestudios.
Project: eyeline-labs.github.io/Virtu…
👉Join us to be the next one empowering #filmmaking with #AI:
Winter 2025/Spring 2026 internship: jobs.lever.co/Eyeline/4eded8…
Summer 2026 internship: jobs.lever.co/Eyeline/85f377…
#hiring #internship #AI #AIResearch #MachineLearning #AIGC #GenAI #VideoGeneration
Paul Debevec retweeted
🥳 #VChain has received the 🏆Outstanding Paper Award🏆 at #ICCV2025 KnowledgeMR Workshop @ICCVConference @KnowledgeMR_ws
🙌Kudos to all the amazing co-authors @ziqi_huang_ @realNingYu @ChenGordon19 @qhnmoon @debfx
- Page: eyeline-labs.github.io/VChai…
- Code: github.com/Eyeline-Labs/VCha…
🎞️𝐂𝐡𝐚𝐢𝐧-𝐨𝐟-𝐕𝐢𝐬𝐮𝐚𝐥-𝐓𝐡𝐨𝐮𝐠𝐡𝐭 for Video Generation🎞️
#VChain is an inference-time chain-of-visual-thought framework that injects visual reasoning signals from multimodal models into video generation
- Page: eyeline-labs.github.io/VChai…
- Code: github.com/Eyeline-Labs/VCha…
Paul Debevec retweeted
Meet Paul Debevec (@debfx) - #SIGGRAPHAsia2025 Featured Sessions speaker and Chief Research Officer at @eyelinestudios powered by @Netflix, this Dec in HK. From image-based lighting to #virtualproduction, his work reshaped CG realism. 🎟 bit.ly/sa25reg
#VFX #Rendering
Paul Debevec retweeted
Excellent article in @FilmmakerMag on ICT's #LightStage and @debfx research - filmmakermagazine.com/131350… btw - why not come and visit the #NextGen #LightStage? - we're building it now...ict.usc.edu/news/essays/ligh…
Paul Debevec retweeted
Join us at #CVPR2025 workshop on Photo-realistic 3D Head Avatars, featuring invited talks by leading experts as well as new benchmark challenges!
@debfx @shalinidemello @psyth91 @YaoFeng1995 Stefanos Zafeiriou @HaoLi81
🔗: kaldir.vc.in.tum.de/nersembl…
Paul Debevec retweeted
“Lux Post Facto: Learning Portrait Performance Relighting With Conditional Video Diffusion and a Hybrid Dataset” by @myq_1997, @vishalm_patel, @wenqi_xian, @JulienPhilip2, @maleewahaha, @realNingYu, @debfx demos a portrait video relighting
method: arxiv.org/abs/2503.14485 (6/14)
Paul Debevec retweeted
Kudos to the research team at our sister company @eyelinestudios. Their latest research paper, 🌊Go-with-the-Flow 🌊, will be presented at #CVPR2025!
Based on their research, we believe this could allow artists in the future to leverage these new techniques to direct the motion in generated videos, empowering creative control in a wide range of video applications: cut-and-drag animation, transferring movement between videos, first frame editing, camera control via depth warping, and text-to-video 3D scene creation.
Kudos to the amazing team: @RyanBurgert, @Yuancheng_Xu0, @wenqi_xian, Oliver Pilarski, Pascal Clausen, Mingming He, @maleewahaha, @yitong_deng, Lingxiao Li, Mohsen Mousavi, @ryoo_michael, @debfx, @realNingYu, from @eyelinestudios, @Scanline_VFX, @netflix, Stony Brook University, University of Maryland, and @Stanford.
***This is part of the ongoing research and development at @eyelinestudios and we hope to see adoption in these techniques and workflows soon.
Paper: arxiv.org/pdf/2501.08331
Web: eyeline-research.github.io/G…
Code: github.com/Eyeline-Research/…
Models: huggingface.co/Eyeline-Resea…
#MachineLearning #video #VideoGeneration #DiffusionModels #VideoDiffusionModels #OpenSource
Excited to show Sodium Vapor Matting - the ingenious compositing technique that let @iammrvandy dance with animated penguins, recently recreated with @CorridorDigital youtube.com/watch?v=UQuIVsNz… - this Sat at @AcademyMuseum before a screening of Mary Poppins. academymuseum.org/en/program…
