Explore

@chriswolfvision.bsky.social Sep 10, 2026, 6:07 AM

#ECCV2026 is opened by GCs and PCs!

@google.xmirror.bot Sep 10, 2026, 5:15 AM

Welcome to #ECCV2026! 🌟 Google is proud to be a Diamond Sponsor at @eccvconf in Malmö, Sweden (Sept 10–12). Visit us at booth #2 to explore our latest research, connect with our team, and see live demos! Learn more: https://goo.gle/ECCV2026 #GoogleResearch

@eccv.bsky.social Sep 10, 2026, 5:02 AM

Good morning #ECCV2026! We kick off the main conference today at 8am with the opening ceremonies, including the Best Paper Award announcement 🏆

@gpuopen.bsky.social Sep 9, 2026, 6:41 PM

Stable lighting, frame after frame: new research on a one-step diffusion model for GI, presented at #ECCV2026.

💡 Geometrically aligned, temporally stable lighting.
🧠 Aligns well with real-world features & illumination.

Read more ⬇️

gpuopen.com/learn/tempor...

@weinzaepfelp.bsky.social Sep 9, 2026, 4:44 PM

Straight lines, one kilometer away from a computer vision conference #ECCV2026

@yoshitomo-matsubara.net Sep 9, 2026, 4:40 PM

#ECCV2026 Day 2
Discussion, discussion, brainstorming, and discussion

It was a very fruitful day 🤗

@jvgemert.bsky.social Sep 9, 2026, 4:38 PM

@eccv.bsky.social #ECCV2026

How can I organize which posters to see where?

The app cuts off paper titles (ie: unreadable and unusable).

The website's schedule is great, but has no poster IDs next to the titles.

Will we get a handy hardcopy program, with titles, times, and ids?

@eccv.bsky.social Sep 9, 2026, 2:59 PM

2 great days of #ECCV2026 workshops and tutorials are slowly heading to an end, and the main conference is nearing! Use Scholar Inbox to help plan out your days so you get to see all the papers relevant to you!

www.scholar-inbox.com/conference/e...

@dlarlus.bsky.social Sep 9, 2026, 12:41 PM

Still at the PhysAI #ECCV2026 workshop - @niessner.bsky.social

@dlarlus.bsky.social Sep 9, 2026, 11:44 AM

Jerome Revaud at '3D in the era of world models' workshop #ECCV2026

@ducha-aiki.bsky.social Sep 9, 2026, 11:21 AM

One view is enough
@davidpicard.eurosky.social
#ECCV2026

@azadef.bsky.social Sep 9, 2026, 10:05 AM

Interested in world models?

Join us for the last keynote talk at the MELEX #ECCV2026 Workshop today by Prof. Jean Ponce on "Self-supervised learning for world modeling" in Malmömassan C1.

@eccv.bsky.social @bazilas.bsky.social @lanalpa.bsky.social

@eccv.bsky.social Sep 9, 2026, 9:39 AM

We’ve had some inquiries about the #ECCV2026 coffee breaks. The actual coffee breaks (with food) are held in Malmomassan.

@jbhaurum.bsky.social Sep 9, 2026, 9:33 AM

The #ECCV2026 AI for Climate and Conservation workshop is PACKED! But don't worry, we still have more great presentations to come, so pop by and have a listen 🌍
@climateainordics.com @aicentre.dk @eccv.bsky.social

@ducha-aiki.bsky.social Sep 9, 2026, 8:59 AM

Christian Rupprecht
"Are we learning to rediscover geometry?" - our final keynote today starting in 3 minutes.
#ECCV2026

@jbhaurum.bsky.social Sep 9, 2026, 8:52 AM

Magnus Gjerde presenting our new work on our adjoint-formulation for point based 3D reconstruction. Come by and say hi if this sounds interesting to you! #ECCV2026 @eccv.bsky.social

@escorciav.bsky.social Sep 9, 2026, 8:46 AM

@michael-j-black.bsky.social “What is the role of academic computer vision research in the age of increasingly powerful large models? …”

#ECCV2026 🇸🇪

What is the role of academic computer vision research in the age of increasingly powerful large models? Is GPT-6 Astra a step change? How can a researcher have an impact today in academia?

These are the questions I ask myself as I head off to ECCV 2026, a conference I’ve attended since 1992. One of my papers this year is VIGA, a method that takes an image as input and outputs a 3D Blender scene that represents that image. This is a classical inverse-graphics task and VIGA was the first method to solve it using an agentic approach.

The idea is now several years old and the first version of the paper was rejected. This delayed publication significantly. After it was accepted at ECCV, it was quickly surpassed by people using Claude Code for the same purpose. Today GPT-6 Astra blows away all previous results. But we still head off to ECCV to tell the community about our invention that is now fully out of date.

The way academic work often progresses is that one reads recent papers, notices that they have limitations, comes up with a new idea, explores this, publishes it, etc. Any published paper I read today is based on ideas that are at least a year old. And those ideas were based on the literature of the time, which was also a year old. That means that any paper I see at ECCV is likely two years out of date. In AI today, two years means your work is likely irrelevant.

At CVPR this summer I noticed that many authors have not gotten the message. They continue to work on “old” problems that have a long history. This history is based on assumptions about how the “vision problem” will be “solved”. The truth is that it is being solved in a very different way and many of these problems are no longer relevant. Another group of papers focuses on very niche problems where large models likely fail because of insufficient data or lack of business interest. The impactful papers were largely from industry and had long author lists and massive data+compute behind them. These papers were also out of data, describing systems that had been released months before, but at least they served to provide the community with more complete documentation and analysis of commercial systems.

So what should academics do? First, we need to put aside the tools we’ve used for years and start from scratch. Every project should start by trying really hard to solve the problem with existing tools. I would like to see every paper begin with a detailed experimental analysis of how existing models perform and why they fail (if they do). This gives the kind of insight we need today. Then, assuming current models fail, the solution should provide some fundamental insight that will outlive the next release of such models.

Reviewers today still focus on technical novelty. This pushes people to focus on tweaking architectures rather than clearly moving the field forward. Papers need to be judged based on their novel insight and not their novel technical contribution. This is a real shift in thinking but it focuses us on what matters - progress of the field.

If we want there to be a “field” of computer vision, then it can’t become a marginal backwater, focusing on esoteric problems. If you haven’t tried using Astra (or whatever comes next) to solve your problem, then you have not done your homework. This omission should be seen as negatively as not having a previous work section.

Concretely, I think papers should include a new section analogous to “Related Work” where that related work is current models and how they perform on the task. Reviewers should start asking for this and expecting authors to be able to articulate their insights about the limitations of existing large models.

I'm interested in your thoughts

@ducha-aiki.bsky.social Sep 9, 2026, 8:32 AM

Algebraic Optimality for Minimal Solvers and Beyond - Timothy Duff, slides from SfM-DL workshop
#ECCV2026
drive.google.com/file/d/1isjF...

@azadef.bsky.social Sep 9, 2026, 8:07 AM

Want to know more about retrieval models in ecology?

Join us at Malmömassan C1 for the second talk at MELEX #ECCV2026 Workshop by Prof. @sarameghanbeery.bsky.social

@eccv.bsky.social @bazilas.bsky.social @lanalpa.bsky.social

@deblinaml.bsky.social Sep 9, 2026, 8:06 AM

🎨 The 4th AI for Visual Arts (AI4VA) Workshop is happening TODAY @eccv.bsky.social #ECCV2026!

📍 Talks: Stroget 3, Quality View Hotel
🕐 From 13:00 CEST
🖼️ Posters: 15:00–16:00, MalmöMässan Exhibit Hall

Registered virtual attendees can join us via Zoom.

Program details: ai4va-eccv.github.io#program