ICCP 2026 is coming to @princeton.edu, July 13-15! Paper submissions are now open, deadline April 10. Accepted papers published in ICCP Proceedings or IEEE PAMI Special Issue.
Take a sneak peek at already confirmed speakers on our website: iccp2026.iccp-conference.org!
#ICCP2026
How do you mesh this argument with non-rgb imaging? I feel like one of the big splits I’m seeing is that while “world” and video models mature, I can’t exactly just pour spad measurements into my model without first turning them into some kind of intermediate representation
Maybe I'm just missing info, but it feels like ST doesn't do a great job of capturing the value it creates. We have a bunch of luxury apartments going up in Redmond, with a lot of the value created by the light rail station, but I don't see this money going back to ST?
👏 HUGE congrats to the #ICCP2025 award winners for their outstanding contributions!
> me trying my best to not wake up my fiancé while leaving for my 7am flight
The humble bluetooth speaker: DEVICE NOT FOUND, PAIRING, DEVICE NOT FOUND
but socialism bad, and progressive = socialism
Recording of the workshop is now online, big thanks to all the organizers and everyone who attended both in person and online!
neural-bcc.github.io
i like how the pickle bags also come with a free shot of pickle juice at the bottom
This Wednesday (1-6PM, Room 106A) at CVPR @cvprconference.bsky.social we have a great lineup of keynote speakers, posters, and spotlights on neural fields and beyond: neural-bcc.github.io
Have a question you want answered by a panel of experts in the field? Send it to us via: tinyurl.com/bdddf36f
and then there’s the fun question of who is on the hook for paying for repairs
In terms of downtown wayfinding I feel like a couple of these badbois pointing towards pike's place/closest light rail station/other attractions would do 99.9% of the work of a digital display
Free wifi throughout downtown is a great idea, but in NYC a lot of these kiosks quickly turned into
(a) at best a nice graffiti art installation
(b) at worst yet another thing that made the sidewalk narrower and harder to roll a cart/stoller through
laddning fast ⚡
Picture of two llamas
I'm having a lot of trouble locally running llama-2, any suggestions?
They keep spitting and hissing at me whenever I try to chat with them, and using GPUs (grass processing units) isn't speeding up inference.
I’m truly lost on how we got to the stage of “actually, investing in American science is bad” so fast
honestly the most I’ve ever been impressed by an LLM was when chatgpt found a meme I saw a couple years ago based on my my absolutely deranged vague description of what animals / visual elements were in it
Going through airport security, the TSA asked me to “open my burrito” to demonstrate it was in fact a burrito.
For academia (particularly graphics/CV folks) it’s also a hard tradeoff. Why spend time figuring out data capture and low-level camera stuff when generative AI is right there.
You’d be surprised how small the publishing circle of computational photography is. The best/most interesting methods get implemented into products, but if something is too productizable it’s hard to find time/willingness to publish it.
> amazing comp photo paper
> looks inside
> 3 citations
So what you’re saying is I should live in a giant mega RV
this is made more tragic by the fact that the new electrified caltrain absolutely slaps
one of these places has a land shortage with average rents for a 1bd hovering around 3k/month
Versus a random station I found scrolling google maps:
Let’s play a fun game called “who has better land use, silicon valley or literal Japanese farmland”
Everything highlighted in purple is parking or an empty lot around San Jose Diridon:
well maybe future companies should just pull themselves up by their bootstraps and buy a government too
Curious about how cities have changed in the past decade? We use MLLMs to analyse 40 million Street View images to answer this. Do you know that "'juice shops' became a thing in NYC" and "miles of overpasses were painted BLUE in SF"? More at→boyangdeng.com/visual-chronicles (vid ↓ w/ 🔊)
/rant
Getting absolutely no reviewer feedback on a fellowship app feels very unproductive (NSF MSPRF).
With conference rejections I can at least encorporate reviewer feedback for the next submission, but with this NSF app it's like "was my outline bad? did the reviewers hate my font choices?" who knows.
We've extended the submission deadline by 2 weeks to April 25th! #CVPR2025 @cvprconference.bsky.social
Link: neural-bcc.github.io#call4paper
