📢📢📢 Check out SCube, our new generative model which can reconstruct 100^2m high-resolution photorealistic scenes in <20s given only a few images as input! Website: research.nvidia.com/labs/toronto-a… arXiv: arxiv.org/abs/2410.20030 [1/N]

Checkout our latest 4D reconstrucion paper BTimer! Amazing work from Jiawei Ren Jiahui Huang and the team!

📢🚗✨ Excited to announce InfiniCube, our scalable generative model for dynamic 3D driving scene generation with high fidelity and controllability! InfiniCube generates very large-scale (300m×400m ~ 100,000m^2), dynamic 3D driving scenes given HD maps, 3D bounding boxes, and

🔥L4GM code and model weights are finally released! !🔥 Try it and turn your video into a 3D animation in just seconds! Code: github.com/nv-tlabs/L4GM-… Models: huggingface.co/jiawei011/L4GM

I am so proud to be part of this big project. Checkout Cosmos models and see how powerful it is to finetune to physical AI downstream applications. More examples at research.nvidia.com/labs/dir/cosmo…

🔥 GenMol: Travel through chemical space with an efficient fragment-based representation, modern discrete diffusion, and enhanced exploration via fragment re-masking and re-generation! 🔥 paper: arxiv.org/abs/2501.06158 blog: developer.nvidia.com/blog/evaluatin… demo: build.nvidia.com/nvidia/genmol-…

🚀 Introducing DiffusionRenderer, a neural rendering engine powered by video diffusion models. 🎥 Estimates high-quality geometry and materials from videos, synthesizes photorealistic light transport, enables relighting and material editing with realistic shadows and reflections

Checkout our latest CVPR2025 paper. 3D reconstruction can be improved with single-step diffusion model.

Proud to be part of it. Checkout research.nvidia.com/labs/toronto-a… for more examples. GEN3C is also powered by Nvidia Cosmos-Diffusion Model. The 7B video diffusion model enables precise camera control ability to the next level.

🚀Excited to introduce GEN3C #CVPR2025, a generative video model with an explicit 3D cache for precise camera control. 🎥It applies to multiple use cases, including single-view and sparse-view NVS🖼️ and challenging settings like monocular dynamic NVS and driving simulation🚗.

Interested in autonomous vehicles? Join Sanja Fidler at #GTC25 to learn how to leverage NVIDIA Cosmos in AV workflows. Register ➡️ nvda.ws/3QYmAZD Share your questions for our #NVIDIAResearch speaker in comments.

Thank you AK for posting our Cosmos-Transfer1! The code is released at github.com/nvidia-cosmos/… and model is on hugging face!

🚀 Difix3D+ is now open-sourced! Check out the code and try the demo: github.com/nv-tlabs/Difix… We're presenting at #CVPR2025 this Sunday, June 15 — come say hi! 🗣️ Oral: 1:00–1:15 PM CDT, Karl Dean Grand Ballroom 🖼️ Poster: 4:00–6:00 PM CDT, ExHall D (Poster #57)

🚀 Introducing Cosmos-Predict2! Our most powerful open video foundation model for Physical AI. Cosmos-Predict2 significantly improves upon Predict1 in visual quality, prompt alignment, and motion dynamics—outperforming popular open-source video foundation models. It’s openly

Amazing work from Jiahui Huang and the team!! If you want to build genie3 like model, checkout ViPE - the STOA video pose engine which estimate camera parameters and dense metric depth from in the wild videos. Code is release. We will also release our annotated video dataset