Khoa Tuan Nguyen

‼️ Major update to the #ACEZero code base. We added the capabilities of the #ICCV2025 paper on Scene Coordinate Reconstruction Priors.

Gives you, e.g., a RGB-D version of ACE0. In the snipped below, I jointly reconstruct multiple RGB-D scans of ScanNet.

github.com/nianticlabs/...

🌟 Scene Coordinate Reconstruction Priors at #ICCV2025 🌟

Can we learn what a successful reconstruction looks like, and use this knowledge when reconstructing new scenes?

Explainer: youtu.be/RkV6U5xYc20
Project Page: nianticspatial.github.io/scr-priors

Inspiring work by Wenjing Bian et al.!

🔥 ACE-G, the next evolutionary step of ACE at #ICCV2025 🔥

We disentangle coordinate regression and latent map representation which lets us pre-train the regressor to generalize from mapping data to difficult query images.

Page: nianticspatial.github.io/ace-g/

Stellar work by Leonard Bruns et al.!

⏩ FastForward ⏩ A new model for efficient visual relocalization. Accurate camera poses without building structured 3D maps.

nianticspatial.github.io/fastforward/

Work by @axelbarroso.bsky.social, Tommaso Cavallari and Victor Adrian Prisacariu.

The most important aspect when facing data shift is the type of shift present in the data. I will give below a few examples of shifts and some existing methods to compensate for it.🧵1/6

Logarithmic maps are incredibly useful for algorithms on surfaces--they're local 2D coordinates centered at a given source.

Yousuf Soliman and I found a better way to compute log maps w/ fast short-time heat flow in "The Affine Heat Method" presented @ SGP2025 today! 🧵

Yet another quadratic Bezier distance function 🧵,slightly cleaner than last time

Premise: We want to calculate the distance to a quadratic Bezier curve, with as little effort as possible, ideally without evaluating the full quadratic Bezier curve itself, which involves solving a cubic equation.

#DLCProTip: Did you know you can use unsupervised learning to adapt a trained model on the fly to your video in DeepLabCut!?

When you run video analysis, check out “video adaptation” - it reduces jitter and provides better poses! ⬇️

www.nature.com/articles/s41...

Hey graphics friends, has anyone seen an algorithm to make a blue noise point sequence, that used a density map? (non uniform points)

I have some ideas to make some, but i am not finding any prior work and think there's a good chance it exists but im just not finding it.

Implicit surfaces are great, but if you are not Inigo Quilez, it's really hard to control how they look...

That's why I'm really proud to annonce our Eurographics 2025 paper: "Implicit UVs: Real-time semi-global parameterization of implicit surfaces".

I'm very excited to share notes on Probabilistic AI that I have been writing with @arkrause.bsky.social 🥳

arxiv.org/pdf/2502.05244

These notes aim to give a graduate-level introduction to probabilistic ML + sequential decision-making.
I'm super glad to be able to share them with all of you now!

MΛX - Surfel Maintenance for Global Illumination A comprehensive explanation of my implementation of Surfel probe maintenance.

I wrote a blog post on my implementation of the Surfel maintenance pipeline from my Surfel Radiance Cascades project. Most of what I learned came from "SIGGRAPH 2021: Global Illumination Based on Surfels" a great presentation from EA SEED :)
m4xc.dev/blog/surfel-...

views of Oxford colleges from a Leica scanner

To kick off using Bluesky: our new dataset called Oxford Spires. Synchronised, multi-color cameras and lidar in multiple Oxford colleges. Ground-Truth highly accurate 3D maps from tripod scanners. The ideal basis for NeRF/3DGS SLAM research.
dynamic.robots.ox.ac.uk/datasets/oxf...

Schrödinger's cat logic: don't check the new papers, and you haven't been scooped! 🐱📄

How do you manage your work-life balance? And how do you manage your projects? For instance, if you have many ideas but are still busy with a previous one, do you take notes and plan to work on them in the future, or do you delegate and develop them collaboratively with colleagues or students?

See who has blocked you 🫣 and added you to a list on Bluesky.

clearsky.app

Stop watching videos, start interacting with worlds.

Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
cat-4d.github.io
arxiv.org/abs/2411.18613

"I'll have what they are having" for bluesky. The motiviation is to mimic who someone else is following who reports they are having a good experience on bluesky! "I'll have what they are having" for bluesky. The motiviation is to mimic who someone else is following who reports they are having a good experience on bluesky! - follow_theirs.py

I wrote this code to follow the same people someone else is following. I figured that would fix my feed esp if someone is having a good experience I can just "have what they are having"

gist.github.com/hamelsmu/fb9...

Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!

We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423

Can you share the research toolkits you use for 3D visualization and evaluation in your work?
For instance, tools like Rerun, Blender, Matplotlib, PyVista, CloudCompare, or others? Thank you

Hello Bluesky! 🔵 We start our account by having our third guess for Ask Me Anything session #3DV2025AMA!

Noah Snavely @snavely.bsky.social from Cornell & Google DeepMind! 🌟

🕒 You have now 24 HOURS to ask him anything — drop your questions in the comments below!

Keep it engaging but respectful!

Thank you for creating it. It’s really helpful.
Can you add bsky.app/profile/vinc...