Eric Chen

Thanks for all the recommendations! I'll try to check them out

Sad I won't be stopping in Phoenix, but do you have any other recommendations of places to see in Tucson?

This work was done during my internship at Snap Research, before starting my PhD, with Di Liu, Sizhuo Ma, Michael Vasilkovsky, Bing Zhou, Qiang Gao, Wenzhou Wang, Jiahao Luo, Dimitri Metaxas, @vincentsitzmann.bsky.social, and Jian Wang

Project Page: echen01.github.io/instamoji-su...

If you're at @wacvconference.bsky.social tomorrow come see our poster on Snapmoji! It's our system to generate and animate 3D avatars of yourself.

I'll be at Poster location 51 from 4:00-5:45 on Sunday!

This work was done during my internship at Snap Research, before starting my PhD, with Di Liu, Sizhuo Ma, Michael Vasilkovsky, Bing Zhou, Qiang Gao, Wenzhou Wang, Jiahao Luo, Dimitri Metaxas, @vincentsitzmann.bsky.social , and Jian Wang

Project Page: echen01.github.io/instamoji-su...

Haha that’s awesome

Wow, it seems like the Olympics broadcast is using Gaussian splats now. Some "spikeys" at the 10 second mark

The demise of Black Friday has been greatly exaggerated

Dataset Distillation for Pre-Trained Self-Supervised Vision Models Distilling image datasets to a single sample per class to train classifiers on top of pre-trained self-supervised vision models.

Happy to finally share our latest work on Dataset Distillation!

"Dataset Distillation for Pre-Trained Self-Supervised Vision Models," set to appear at #NeurIPS 2025!

We learn 1 image per class to train linear heads for pre-trained models.

linear-gradient-matching.github.io

More in thread 🔽

DUSt3R et al. are impressive, but how do they actually work? We investigate this in our project 𝘜𝘯𝘥𝘦𝘳𝘴𝘵𝘢𝘯𝘥𝘪𝘯𝘨 𝘔𝘶𝘭𝘵𝘪-𝘝𝘪𝘦𝘸 𝘛𝘳𝘢𝘯𝘴𝘧𝘰𝘳𝘮𝘦𝘳𝘴!⁣

We share findings on the iterative nature of reconstruction, the roles of cross and self-attention, and the emergence of correspondences across the network [1/8] ⬇️

xfactor!!

It seems like back in the 2000s, while arxiv did exist, most CS researchers would just host their preprints on their personal sites. But now in ML, putting your paper on arxiv seems like a must. What do you think changed? Could this policy mean the return of self-hosted preprints?

Curated Data for Efficient Learning The ICCV 2025 Workshop on Curated Data for Efficient Learning

Our schedule is live!

curateddata.github.io/schedule.html

We have posters, oral presentations, and invited talks from @zhuangl.bsky.social, @sarameghanbeery.bsky.social, @andrewowens.bsky.social, @phillipisola.bsky.social, and Alyosha Efros!

See you in Hawaii!

#ICCV2025 @iccv.bsky.social

Come see our talk on "Pocket Time-Lapse" at SIGGRAPH today at 4pm in the Image Representation, Editing, & Generation session!
West Building, Rooms 118-120

3D render of dogs on skateboards

Congrats, love this figure!

Excited to share our new work at @acm.org Transactions on Graphics/@acmsiggraph.bsky.social! We use coded noise to add an invisible watermark to lighting that helps detect fake or manipulated video. (1/2)

At ICML, we're presenting a paper on uncertainty-aware surface reconstruction!

Compared to previous approaches, we are able to completely remove the need for recursive linear solves for reconstruction and interpolation, using geometric GP machinery.

Check it out!

🚨🚨 WiGRAPH CONFERENCE COFFEE @ SIGGRAPH '25 🚨🚨

Sign up now to be randomly matched with peers for a SIGGRAPH conference coffee!

📢 I'm excited to share BrepDiff, our single-stage B-rep diffusion model, which enables unconditional generation and editing of B-reps.
This work will be presented at #SIGGRAPH2025 with @mingilikesmangos.bsky.social, @dongsuzhang.bsky.social, and Young Min Kim.
🌐: brepdiff.github.io
1/8

I think it often refers to parameterizing a camera's ray bundle with Plucker coordinates

The multi-plane camera at the Walt Disney Family museum. It’s huge!