Principal Research Scientist at NVIDIA, having fun with low-level computer vision perception. Beach volleyball fanatic. Views are my own.
Joined March 2009
- Tweets330
- Following443
- Followers1.2K
- Likes639
Stoked about the release of the code for our work on scene flow, which was nominated for the best paper award at @CVPR 2025. Take a look, play with it, and let us know what you think!
github.com/nvlabs/zero-msf
🎉 [CVPR 2025] ZeroMSF Code Release!
3D scene flow from a single camera, with no fine-tuning on new domains? That’s the challenge we tackled in Zero-MSF (Zero-shot Monocular Scene Flow).
💡 Motivation
Scene flow captures both geometry and motion, but existing methods crumble when moving beyond their training set. We asked: Can we build a foundation-style model that generalizes—out of the box—to any scene?
🔬 Our Answer
• Large-scale synthetic pre-training (1M+ dynamic samples)
• A unified geometry-motion parameterization
• Zero-shot inference on real-world videos—no extra training, just run it!
🤝 Huge Thanks
To my brilliant collaborators AbhishekBadki, HangSu, @0razio and my amazing advisor @jtompkin for making this possible.
👉 Dive In: research.nvidia.com/labs/lpr…
Join us today to learn how to push the boundaries of stereo depth estimation!!
Come and say 👋 tomorrow (06/13) for our oral (1pm, Karl Dean Ballroom) and poster sessions (4pm, ExHall D, #81)!
#CVPR2025 @CVPR @CVPRConf @NVIDIAAIDev @NVIDIARobotics #NVIDIA
If you're at #CVPR2025 don't miss @YiqingLiang2's talk on our scene flow estimation work, which was also a CVPR Best Paper Award nominee!
Collaboration between @NVIDIAAI and @BrownUniversity
Heading to Nashville for @CVPR ! 🎸
I’ll be presenting the @nvidia internship project —
“Zero-Shot Monocular Scene Flow Estimation in the Wild” (Best Paper Candidate)
🗓 Sunday, June 15
🕘 Poster + Oral Presentation: Morning session
🔗 research.nvidia.com/labs/lpr…
#ComputerVision #SceneFlow #NVIDIAResearch #3DVision #CVPR2025
I'm very excited about this work led by @bowenwen_me, in which we show that high-quality synthetic data and architectural design choices that allow scalability can really push the envelope of stereo-based depth estimation.
Could #AI revolutionize stereo depth estimation?
Utilizing a massive dataset of stereo pairs, FoundationStereo is designed as a foundation model with strong zero-shot generalization and automatic self-curation pipeline.
Details from #NVIDIAResearch ➡️ nvlabs.github.io/FoundationS…
Orazio Gallo retweeted
Zero-Shot Monocular Scene Flow Estimation in the Wild
@YiqingLiang2, Abhishek Badki, Hang Su, @jtompkin @0razio
tl;dr: Dust3r predicting also a flow, but really - training recipe how to train on many scene flow datasets, especially w/o GT flow
arxiv.org/abs/2501.10357
Proud of this project led by @daniel_lichy. FoVA-Depth is our answer to a problem we experience in many projects: for uncommon cameras, eg fisheye, we don't have as much training depth data as we do for pinhole cameras.
🚀 Excited to release the code from our #3DV2024 oral presentation: FoVA-Depth: Field-of-View Agnostic Depth Estimation for cross-dataset generalization! 📊
🔗 Project details: research.nvidia.com/labs/lpr…
🔗 Code: github.com/NVlabs/fova-depth (1/8)
📢Doing 3D learning on datasets captured with different camera/image models, eg a mix of pinholes and fisheyes or ERPs?
With #nvTorchCam write the code once and forget about it, and you can even batch them all together!
github.com/NVlabs/nvTorchCam
Let us know what you think!
🎉 Thrilled to introduce nvTorchCam, our new #PyTorch library designed to support the development of models using camera geometry like plane-sweep volumes (PSV) and related concepts like sphere-sweep volumes or epipolar attention, in a camera model-agnostic way! 🚀
🔗 Code: github.com/NVlabs/nvTorchCam
(1/6)
I'll be at @3DVconf next week and I'm hiring! Flag me down if you'd like to join my team to do some cool research on low-level computer vision perception and/or image-based modeling/rendering at NVIDIA! But also, feel free to stop me to say hi :)
We have research #internships roles at @NVIDIAAI!!
Reach out if you're in a PhD program, and are interested in anything 3D (e.g., monocular/multi-view depth estimation, SLAM, SfM, etc.), anything optical/scene flow, anything novel view synthesis.
If you are interested in this position, please fill this brief questionnaire:
forms.gle/rbDirdMZVt2H649r9
Orazio Gallo retweeted
Utilize neural fields to generate authentic novel views from LiDAR. If you're at #ICCV2023, drop by to delve deeper.
📌 Poster: Friday, 10:30 AM, Paper 1719
🎙 Talk: Tuesday, 9 AM at the NeRF4ADR workshop
Neural LiDAR Fields for Novel View Synthesis
abs: arxiv.org/abs/2305.01643
project page: research.nvidia.com/labs/tor…
If you attend SIGGRAPH make sure to check this out, it's really cool!
In about a week @SIGGRAPH, we will showcase an AI-Mediated 3D Video Conference system at Emerging Technologies, where you can talk to people in 3D using only a webcam + GenAI. It also features Live 3D Portrait and many more! Check it out nvidia.com/en-us/events/sigg…
If you are a PhD student looking to intern in a great research environment, don't miss this opportunity!
Orazio Gallo retweeted
At NVIDIA Research, we are seeking research intern candidates who are interested in the topic of Large Language Models (LLM) compression: pruning, sparsity, architecture design, efficient training, and architecture search.
Please submit your CV here: bit.ly/intrs
Orazio Gallo retweeted
A new algorithm exposes fascinating underdrawings of old master paintings! Check out the results for this painting by Leonardo da Vinci from @NationalGallery and others here:
ieeexplore.ieee.org/document…
@pdragotti @imperialcollege @imperialeee
Orazio Gallo retweeted
🎉 Congratulations to Ken Museth of NVIDIA, this year's ACM @SIGGRAPH Practitioner Award recipient. His transformative work on #OpenVDB reshapes 3D modeling and animation, empowering global creatives.
#SIGGRAPH2023
Orazio Gallo retweeted
In the past few years, we've been working a lot on image deblurring & restoration. Addressing this very relevant problem can be done from multiple angles & multiple strategies. I was recently invited to give a talk on this topic 🧵 [1/9]. youtube.com/watch?v=7ZkB3ASP…
Check out this amazing work from @seungkim0123 et al. at @NVIDIAAI!
📢Excited to announce "NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models"!
research.nvidia.com/labs/tor…
Joint work w/ the amazing @brad19brown @kangxue_yin @karsten_kreis @K_S_Schwarz @lidaiqing @robrombach @abtorralba @FidlerSanja
@NVIDIAAI #CVPR2023