Riccardo de Lutio
@RdeLutio
Followers
263
Following
608
Media
3
Statuses
120
Research scientist @NVIDIAAI, outdoors and mountain enthusiast.
Joined January 2020
1/ #NVIDIAGTC We’re excited to share that ChronoEdit-14B model and 8-step Distillation LoRA (4s/image on H100) are released today. 🤗 Model https://t.co/X3diGAY42p 🤗 Demo https://t.co/2xfiRo6wij 💡ChronoEdit brings temporal reasoning to image editing task. It achieves STOA
5
34
103
Thrilled to share our latest work: SimULi! We extend 3DGUT to LiDAR sensors and propose a factorized representation of camera and LiDAR Gaussians. This improves the camera vs LiDAR accuracy tradeoff while significantly accelerating rendering. Learn more:
[1/N] Excited to introduce "SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms." We extend 3DGUT with LiDAR support and render a wide range of sensors 10-20x faster than ray tracing and 1.5-10x faster than prior rasterization work. https://t.co/Q9J2T5cjLj
0
0
4
Our team at Nvidia Spatial Intelligence Lab is hiring PhD research interns for 2026! https://t.co/CkIzwirg4T If you’re excited about fast video models, generative world simulators, or 3D foundation models, please reach out by email or apply directly https://t.co/97LJFZceyi
lnkd.in
This link will take you to a page that’s not on LinkedIn
5
32
217
Come and join us at NVIDIA! Aside from many intern openings, if you are graduating 2026 and will be looking for full-time job, let us know so we can keep you posted about our full-time hiring timeline!
Our team at Nvidia Spatial Intelligence Lab is hiring PhD research interns for 2026! https://t.co/CkIzwirg4T If you’re excited about fast video models, generative world simulators, or 3D foundation models, please reach out by email or apply directly https://t.co/97LJFZceyi
11
40
350
📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a
19
71
250
[1/N] 🎥 We've made available a powerful spatial AI tool named ViPE: Video Pose Engine, to recover camera motion, intrinsics, and dense metric depth from casual videos! Running at 3–5 FPS, ViPE handles cinematic shots, dashcams, and even 360° panoramas. 🔗 https://t.co/1mGDxwgYJt
13
105
452
Can we learn to complete anything in Lidar without any manual supervision? Excited to share our #ICML2025 paper “Towards Learning to Complete Anything in Lidar” from my time at @nvidia with @CristianoSalto @NeeharPeri @meinhardt_tim @RdeLutio @AljosaOsep @lealtaixe! Thread🧵👇
1
12
60
🚀 InfiniCube is accepted to #ICCV2025 Code will be released at: https://t.co/HGyWWYHS1G See you all in Hawaii!!
github.com
[ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models - nv-tlabs/InfiniCube
📢🚗✨ 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
1
8
65
🚀 We just open-sourced Cosmos DiffusionRenderer! This major upgrade brings significantly improved video de-lighting and re-lighting—powered by NVIDIA Cosmos and enhanced data curation. Released under Apache 2.0 and Open Model License. Try it out! 🔗 https://t.co/h87zZhodp0
🚀 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
9
123
525
📢 GEN3C is now open-sourced, with code released under Apache 2.0 and model weights under the NVIDIA Open Model License! 🚀 Along with it, we're releasing a GUI tool that lets you specify your desired video trajectory in 3D — come play with it and generate your own! The
🚀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🚗.
1
28
137
🎙️ Super excited to invite you all to our #CVPR2025 tutorial!! Join us for a hands on session to learn how to combine rendering and simulation through #kaolin #simplicits #3dgrt from the #NVIDIA Spatial Intelligence Lab. June 11 morning. Invitation page:
Curious about 3D Gaussians, simulation, rendering and the latest from #NVIDIA? Come to the NVIDIA Kaolin Library live-coding session at #CVPR2025, powered by a cloud GPU reserved especially for you. Wed, Jun 11, 8-noon. Bring your laptop! https://t.co/joCH5DDrNk
0
3
11
The time for new architectures is over? Not quite! SeNaTra, a native segmentation backbone, is waiting, let's see how it works 🧵 https://t.co/2I9nuLBsSz
arxiv.org
Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping...
3
41
207
Join us in building the next generation of Neural Reconstruction and Generation algorithms for AV and robotics simulation!
📢Our team at @NVIDIAAI is again looking for Research Scientists and Engineerings to help us push the boundaries of Neural Reconstruction and Generation in AV and Robotics simulation! Check out our latest work at https://t.co/dUOStf9kbR, and if interested, reach out directly!
0
0
1
🌟gsplat🌟just integrated 3DGUT, which allows training and rendering 3DGS on *distorted* pinhole/fisheye cameras, as well as rolling shutter effects! > Checkout this NVIDIA tech blog https://t.co/LGym5auoxf > Sweepstakes to win a 4090 https://t.co/KYACvE6NGf
2
30
185
📢 3DGUT has also been integrated into gsplat! Checkout the @NVIDIAAI blog ( https://t.co/hRTQt1Cq2V) and participate in the sweepstake for the chance of winning an Nvidia 4090 GPU: https://t.co/wnI7L4lvYy Great job @ruilong_li (amazing start at @NVIDIAAI) and @wilson_over!
nvidia.com
Grab a camera and transform your shots into a 3D scene using NVIDIA 3DGUT software for a chance to win an NVIDIA RTX™ 4090 Ti. Showcase your skills with the latest in 3D Gaussian Splatting technology.
🌟gsplat🌟just integrated 3DGUT, which allows training and rendering 3DGS on *distorted* pinhole/fisheye cameras, as well as rolling shutter effects! > Checkout this NVIDIA tech blog https://t.co/LGym5auoxf > Sweepstakes to win a 4090 https://t.co/KYACvE6NGf
2
16
77
🔊New NVIDIA paper: Audio-SDS🔊 We repurpose Score Distillation Sampling (SDS) for audio, turning any pretrained audio diffusion model into a tool for diverse tasks, including source separation, impact synthesis & more. 🎧 Demos, audio examples, paper: https://t.co/XIcoqKb1I9
6
75
359
A big quality of life improvement in gsplat just dropped! Full nerfstudio viewer support in gsplat now!
🚀 Update on gsplat viewer We’ve modularized the awesome @nerfstudioteam viewer into nerfview — now gsplat (and anyone else) can use it as a powerful viewer and exporter! 🔗 gsplat: https://t.co/T6A9Wvm5Hd 🔧 nerfview: https://t.co/6btv0eJyXG
1
12
120
What if you could control the weather in any video — just like applying a filter? Meet WeatherWeaver, a video model for controllable synthesis and removal of diverse weather effects — such as 🌧️ rain, ☃️ snow, 🌁 fog, and ☁️ clouds — for any input video.
3
14
68
Accepted to ICML 2025 🚀
0
11
88
Check out @jonstephens85's tutorial on how to use the 3DGRUT codebase to generate some cool results. The code is released under Apache 2.0 so go and try it out yourself! https://t.co/VJMIUQ5yo2
github.com
Ray tracing and hybrid rasterization of Gaussian particles - nv-tlabs/3dgrut
Do you want to create gaussian splatting scenes with a lot less photos? This first impressions and tutorial is for you! I show you how @NVIDIAAIDev's 3DGRUT works and how to run it on your own PC! Link to video: https://t.co/6H4DL7Sjxu
#3d #GaussianSplatting #computervision
1
9
43