That's the raw 3d scan quality I like to see #photogrammetry #3Dscanning #photometry

🔥#Rodin Gen-1 has been tested by over hundreds Game Developers at #GDC2024 Expo. 🏃We will keep improving the results and looking forward to meeting you in May! Join the waitlist: forms.office.com/Pages/Response…

Thanks AK ! DiLightNet has been accepted to #SIGGRAPH and we can now acknowledge the authorship🎉🎉🎉 Check dilightnet.github.io for more results!

Thanks AK for sharing our work! Neural Gaffer is an end-to-end 2D relighting diffusion model that accurately relights any object in a single image under various lighting conditions. Moreover, by combining with other generative methods, our model enables many downstream 2D

Super excited to be in Seattle this week for #CVPR2024 to present our recent work 𝐓𝐮𝐫𝐛𝐨𝐒𝐋: 𝐃𝐞𝐧𝐬𝐞, 𝐀𝐜𝐜𝐮𝐫𝐚𝐭𝐞 𝐚𝐧𝐝 𝐅𝐚𝐬𝐭 𝟑𝐃 𝐛𝐲 𝐍𝐞𝐮𝐫𝐚𝐥 𝐈𝐧𝐯𝐞𝐫𝐬𝐞 𝐒𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞𝐝 𝐋𝐢𝐠𝐡𝐭. Joint work with Maxx Wu, Wenzheng Chen, David Lindell,

Our 2013 SIGGRAPH paper "Femto-Photography: Capturing and Visualizing the Propagation of Light" has received the 2024 Test of Time Award! It's given to papers "that have had a significant and lasting impact on computer graphics and interactive techniques over at least a decade".

We have updated the paper Gaussian Splashing with more results and experiments. Please visit the project page for more information! Link: gaussiansplashing.github.io TL;DR: Gaussian Splashing is a unified framework combining 3D Gaussian Splatting and Position-Based Dynamics.

Thanks AK ! Check our project page meshformer3d.github.io for more results & demo!🥂

GS^3: Efficient Relighting with Triple Gaussian Splatting Abstract: We present a spatial and angular Gaussian based representation and a triple splatting process, for real-time, high-quality novel lighting-and-view synthesis from multi-view point-lit input images. To describe

always pleased to see capture results of this quality

the name "world model" is insane

Introducing NVIDIA Cosmos, an open-source, open-weight Video World Model. It's trained on 20M hours of videos and weighs from 4B to 14B. Cosmos offers two flavors: diffusion (continuous tokens) and autoregressive (discrete tokens); and two generation modes: text->video and

Big thanks to AK for the shoutout!🥳 Our #SIGGRAPH2025 paper RenderFormer does end-to-end rendering from triangle meshes to images, with global illumination💡 —— using just a simple transformer!!!🪄 🔗Project page: microsoft.github.io/renderformer 💻Code: github.com/microsoft/rend…