Chris Offner

When vision people do graphics, they call it "image synthesis." When graphics people do vision, they call it "inverse rendering". ;)

Huge props to Lord and Miller for stepping up and doing what directors like Nolan are too cowardly to do: be up front and give loud and generous credit to their VFX team. Great directors don’t need to lie about how their movies are made; the work speaks for itself.

Any idea why Scholar Inbox cannot find the paper arxiv.org/abs/2512.11508? @si-cv-graphics.bsky.social @andreasgeiger.bsky.social

If you want me to consider reading something, you have to convince me that you care way more than I do.

All the "you need to learn AI skills or you'll get left behind" things are patently nonsense. It's easy to use and only becomes easier to use over time. If there's skill it's in knowing what it does well and what is does poorly

This is a really good point. While there are men and women on the 'sceptic' side of all these debates, I don't know of any women on the AI 'booster' side. It's really a guy thing

Looking forward to a busy #ICCV2025. I will give three (very different) talks at workshops and tutorials, see info below. We also present two papers, ACE-G and SCR Priors. And it's the 10th (!) anniversary of the R6D workshop, which we co-organize.

#TTT3R: 3D Reconstruction as Test-Time Training TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required! 🔗Page: rover-xingyu.github.io/TTT3R We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D!

🚀 Europe’s first exascale supercomputer is here! JUPITER, launched in Germany, is the EU’s most powerful system and fourth fastest worldwide. 100% powered by renewables, it has also ranked first in energy efficiency. It will boost AI, science, and climate research. Read more - europa.eu/!vcWBqW

There is a lot to hate about the politics of the silicon valley right, but they do actually want to build stuff, and I would prefer if the left didn't cede "we should be able to build stuff" to the right.

I can't* fathom why the top picture, and not the bottom picture, is the standard diagram for an autoencoder. The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?

Great video on the convergent evolution from hierarchical military command structures to cybernetics to centralized AI coordination across political ideologies: www.youtube.com/watch?v=mayo...

In general I think 3D vision would do well to take some inspiration from Bayesians. I guess these days they lost their glamour, but imo it's a very nice way of thinking that feels somewhat lost currently.

"It is beautiful. It is elegant. Does it work well in practice? Not really. This is often the caveat we face in research: the things that are beautiful don't work and the things that work are not beautiful." – Daniel Cremers

"As roboticists and computer vision people [outside of big tech], do we have to just wait for the next foundation model?" I share the frustration. It's disempowering when most major progress recently is downstream of "foundation models" that you don't have the compute or data to train yourself.

We're live on bluesky! bibliome.club is the platform for creating, collaborating on and sharing reading lists with your Bluesky network - open source and decentralised via ATProto.

Yay, DINOv3 is out! SigLIP (VLMs) and DINO are two competing paradigms for image encoders. My intuition is that joint vision-language modeling works great for semantic problems but may be too coarse for geometry problems like SfM or SLAM. Most animals navigate 3D space perfectly without language.

What are the best resources to learn about VLMs? Papers, tutorials, courses, blog posts, whatever is good. I can read the Kimi-VL or GLM tech reports and follow the breadcrumbs but I'd appreciate any and all recommendations towards a useful VLM curriculum! 🙏

Ensuring the robots can’t take our jobs by teaching the robots functional programming

I was not aware that the #ECCV2024 oral recordings are publicly available... So here is the #ACEZero talk: eccv.ecva.net/virtual/2024...

DUNE is a great universal image encoder which works for a large class of tasks and beats its teacher MASt3R on map free localization. #cvpr2025 We use it a lot already, I recommend it. (keynote @ Paris by @dlarlus.bsky.social )

I agree 100%. It's one thing to criticize corporate practices, the social impact, ethics, or future risks. But I watch in total awe how it writes in a few seconds a well documented program in a language/API I don't know, while they complain "but it might have a bug and requires a pass or two" O_o

My X feed's reaction to Dario Amodei's recent interviews.

Collective intelligence is only as strong as our collective attention.

Nice demonstration of the capabilities and failures of videogen models. youtu.be/US2gO7UYEfY

Depending on who you talk to, a “deep dive” can mean spending seven years leading a field of research, or it can mean having six words on a slide instead of two.

Ambitious projects are happening in Zurich’s AI scene. www.theverge.com/news/669238/...

This pattern is going to repeat in one domain after another, and gradually force us to admit that 60% of every job is networking, knowing who to trust, and doing poorly justified risk/benefit assessment.

VRG from CTU in Prague has 9 of its members listed as outstanding reviewers. Congratulations to @gkordo.bsky.social, @billpsomas.bsky.social , @stojnicv.xyz , Pavel Suma, @ducha-aiki.bsky.social , Miroslav Purkrábek, Tomas Vojir, and Yaqing Ding.

🎉💡 Impressions from today’s ETH Augmented Reality Lab (ETHAR) opening, a new hub dedicated to advancing core technologies in AR, in collab with Google. scientists.@christianholz.bsky.social @ethzurich.bsky.social

What happens when ETH Zurich teams up with Google to shape the future of #AugmentedReality? We're opening a new #Researchhub that brings together top minds to tackle one of the biggest challenges in tech: seamlessly blending the digital and physical worlds. Read more:

Trying to wrap my head around fwd/bwd kinematics for imitation learning, so I built a fully‑differentiable kinematic hand skeleton in JAX and visualized it with @rerun.io new callback system in a Jupyter Notebook. This shows each joint angle and how it impacts the kinematic skeleton.

Please share widely: The EPFL Geometry Computing Laboratory is launching its third call for an Artist / Designer Residency for the fall of 2025! More information on how to apply here: www.epfl.ch/labs/gcm/ope... #design #art #residency #research

kids these days, am I right? @clairebraeuer.bsky.social

Just incredible

I wrote a document describing how we want to make it possible to build high level and easy-to-use node group assets for physics simulations and more. #b3d #devfund #GeometryNodes devtalk.blender.org/t/declarativ...

Here's a recording of my 3DV keynote from a couple weeks ago. If you're already familiar with my research, I recommend skipping to ~22 minutes in where I get to the fun stuff (whether or not 3D has been bitter-lesson'ed by video generation models) www.youtube.com/watch?v=hFlF...

I asked "on the other platform" what were the most important improvements to the original 2017 transformer. That was quite popular and here is a synthesis of the responses:

“The final frontier is not space — it’s status.” www.slater.works/posts/post-s...

Wisdom is knowing when to rely on science and when to believe in a bit of magic. Tonight it’s time for the Böögg!

The unfortunate reality is that open ai research community has solidified on the bad site over the past few months. Much more ties, ongoing collaborations on group chats, irl meetups, larger audience (especially post-DeepSeek effect).

This was helpful. Also worth noting that Bluesky remains a very fraught place for AI discussions for a variety of reasons, good & bad, but with the impact of keeping a lot of the most relevant AI news, paper discussions & biggest names on X That might change, but it hasn’t yet. Still posting, tho.