Nikos Athanasiou
@_nikos_athan
PhD @ MPI_IS
Contact. Contact. Contact. For spatial intelligence, this is what location, location, location is in real estate. InteractVLM predicts 3D contacts on humans and objects from a single image. This is a key step in training machines to interact with the 3D world.
🔥 New InteractVLM Models Released! (#CVPR2025) 🔹 Single Model for Joint Human-Object Contact 🔹 3D Human Contact trained on more data, now supports foot-ground contact 🔹 Direct Contact Estimation on Images (2D) 🔗 [Code] github.com/saidwivedi/Int…
📢 R u in Athens on July 22? 📢 Check out the #ComputerVision Day @ ArchimedesAI! Talks: 👉@VickyKalogeiton: 'Efficient Brains that Imagine' 👉Dimitris Samaras: 'From Saliency to Scanpaths: 20 years of Wandering Eyes' 👉@dimtzionas: 'Towards In-the-Wild Understanding of 3D…
One of our latest release "MoCapade 3.5" features. foot locking!
When I first started testing Meshcapade eight months ago, it had the typical foot sliding issue and didn’t capture hand movements. Over time, they’ve improved it, and honestly, version 3.5 delivers remarkably efficient capture
Physical intelligence for humanist robots. At @meshcapade we've built the foundational technology for the capture, generation, and understanding of human motion. This blog post explains how this enables robot learning at scale. medium.com/@black_51980/p… perceiving-systems.blog/en/news/toward…
It's clear that video diffusion models know a lot about the 3D world, material properties, and lighting. The trick is to get control over these. With a tiny amount of synthetic data, we can train a video model to realistically relight a single image. This is a neat trick that…
🚀 Introducing GenLit – Reformulating Single-Image Relighting as Video Generation! We leverage video diffusion models to perform realistic near-field relighting from just a single image—No explicit 3D reconstruction or ray tracing required! No intermediate graphics buffers,…
🥁 📢🏅 The DAMON Challenge at the 3rd RHOBIN Workshop @ #CVPR2025 was a big success! With 51 teams and 108 submissions, it was fiercely competitive — pushing performance 38% to 122% beyond the DECO baseline in the Body and Semantic Contact Estimation tracks!!
🚀🚀 The 3rd RHOBIN challenge @CVPR on reconstruction of humans, objects, and interactions is live now! Past winners have gone on to publish in top conferences - it could be you this time! We also have exciting rewards from our sponsors. 🧵 1/3
Join us today (June 12-9:00)! Rhobin workshop is happening today @CVPR. 🕑 9:00-12:00 📍Room 212 🎤Great talks by our speakers @FedericaBogo, @ericyi0124, @angelayao101, @jiajunwu_cs, +panel discussion! 💻 Challenge winners announcement + talks!
Interested in the latest progress in Reconstructing Human-Object Interaction? Join the #CVPR2025 Rhobin worskshop: 🕑 9:00-12:00 📍Room 212 👉 Exciting talks by @FedericaBogo, @ericyi0124, @angelayao101, @jiajunwu_cs, +panel discussion! 👉 Challenge winners announcement + talks!
If you’re not in freefall, you’re likely contacting something. Yet 3D human-object interaction (HOI) reconstruction remains underexplored. PICO (#CVPR2025) recovers humans 🏃♂️, objects 🏓, and their interactions 👉🍎- all in 3D, from just a single internet image. 1/11
Why does 3D human-object reconstruction fail in the wild or get limited to a few object classes? A key missing piece is accurate 3D contact. InteractVLM (#CVPR2025) uses foundational models to infer contact on humans & objects, improving reconstruction from a single image. (1/10)
Capturing 3D human pose and motion has made great progress but humans interact with 3D objects. Training robots from demonstration requires that we estimate the human, the object, and the contacts in 3D. PICO is a step towards that goal. At CVPR2025.
Final video in our #CVPR2025 series: PICO 🤝📦 By Alpár Cseke, Shashank Tripathi, Sai Kumar Dwivedi, Arjun S. Lakshmipathy, Agniv Chatterjee, Michael J. Black, and Dimitrios Tzionas, in collaboration with the Max Planck Institute for Intelligent Systems (@MPI_IS), Carnegie…
If you're an international PhD student at Harvard studying computer vision and your visa is cancelled, reach out to me or others in Europe. Don't despair. I'm sure we can find you a great place to carry on your research.
This is a smart suggestion. If language is the issue, review in your native language and then translate. Please respect your colleagues and fellow researchers!
The use of AI in reviewing is a growing problem. Several of my ICCV papers have AI reviews -- one reviewer was so lazy that they left in the prompts! A common refrain that I hear is that people have difficulty writing in English and need to use AI to clean up their review.…
We're hiring! IMAGINE @ École des Ponts (Paris area) is opening a 4-year "CV for X" researcher position: – competitive salary – no teaching load – starting pkg ≈ 2 PhDs – goal: impactful core AI + X (climate, biodiversity, robotics...) Apply by May 31: imagine-lab.enpc.fr/wp-content/upl…
Introducing Chapter-Llama [#CVPR2025], a framework for 𝐯𝐢𝐝𝐞𝐨 𝐜𝐡𝐚𝐩𝐭𝐞𝐫𝐢𝐧𝐠 using Large Language Models! 🎬🦙 Check it out: 📄 Paper: arxiv.org/abs/2504.00072 🔗 Project: imagine.enpc.fr/~lucas.ventura… 💻 Code: github.com/lucas-ventura/… 🤗 Demo: huggingface.co/spaces/lucas-v…