iiinova — where your digital self keeps evolving

Reposted by Adam Ce

Markus Schütz @m-schuetz.bsky.social · 17/11/2025

📢 Looking for 1 PhD student (3 years) in Vienna! We have an open position for someone to tackle MASSIVE 3D datasets and turn them into instant visuals for display, editing, and interacting! applications.cg.tuwien.ac.at/node/5

021

Reposted by Adam Ce

Ulrike Franke @rikefranke.eu · 19/10/2025

How do people with kids get anything done, ever? I’m serious, whenever I see someone roughly my age accomplish anything these days, first thing I do is check whether they have kids. Written a book? Cool. Written a book *while having kids*? You’re a GOD.

4248424

Reposted by Adam Ce

Tatarigami @tatarigami.bsky.social · 10/09/2025

My grandmother took a tougher stance on TV volume with my grandfather than Trump did on Russia penetrating NATO airspace with drones.

20778125

Reposted by Adam Ce

Andrei Bursuc @abursuc.bsky.social · 25/08/2025

Slurm for scheduling busy families with kids on weekends: parents submit their jobs/chores/activities requests (individual or collective) and they are queued based on priority, duration, calendars, karma, etc.

182

Adam Ce @adamcelarek.bsky.social · 22/08/2025

@derstandard.at ist eigentlich bekannt, dass die Webseite im Firefox mobile nicht mehr funktioniert? sie ladet ständig neu, was dann auch Interaktion verhindert.

010

Reposted by Adam Ce

Justin Weinberg @dailynous.com · 28/07/2025

Wiley officially closes the Journal of Political Philosophy, which was abandoned by its editorial team and shunned by academics after Wiley attempted moves that would have compromised the journal's editorial independence.

dailynous.com

Journal of Political Philosophy Officially Ends - Daily Nous

"The Journal of Political Philosophy will cease publication effective January 1, 2026." That's from an email sent by the journal's publisher, Wiley, earlier today, calling the move "a difficult decisi...

412943

Reposted by Adam Ce

Yining Karl Li @yiningkarlli.bsky.social · 07/07/2025

At SIGGRAPH 2025, Intel, Disney, & Chaos are doing a course on the nitty gritty details of implementing path guiding methods in 3 production renderers: Cycles, Hyperion, and Corona. I helped write the course notes: 80 pages of great stuff! Coming soon. s2025.conference-schedule.org/presentation...

08416

Reposted by Adam Ce

Keith Fitzgerald @keithfitzgerald.bsky.social · 26/06/2025

Worth a watch: Head of Signal, Meredith Whittaker, on so-called "agentic AI" and the difference between how it's described in the marketing and what access and control it would actually require to work as advertised.

204109314360

Reposted by Adam Ce

Tuffy @smtuffy.bsky.social · 22/06/2025

It’s fun when there’s a major geopolitical event that features zero good guys

1142

Reposted by Adam Ce

Quantian @quantian.bsky.social · 21/06/2025

The reason Elon made Grok in the first place was because he assumed OpenAI was turning the secret “woke” dial up too high and small parameter tweaks could make it right-wing. Now he has realized the only way to get the AI to agree with him is to lobotomize it by rewriting the entire training set.

1032065504

Reposted by Adam Ce

Jon Barron @jonbarron.bsky.social · 28/04/2025

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...

youtube.com

Radiance Fields and the Future of Generative Media

YouTube video by Jon Barron

25912

Reposted by Adam Ce

Melaine Le Roy @subfossilguy.bsky.social · 28/05/2025

SPEECHLESS BEFORE / AFTER #BLATTEN The magnitude of destruction after the 3:24 pm collapse of Birch Glacier is immense! 😱 All the forest has been razed and the ice/wood/debris dammed the Lonza river 🌊 Some buildings of Blatten are buried 🏠 📷 Pomona

17626369

Reposted by Adam Ce

Chris Offner @chrisoffner3d.bsky.social · 06/02/2025

Fantastic "Deep Dive into LLMs" video by @karpathy.bsky.social, a high-level but detailed explainer of how LLMs are trained and fine-tuned, and what they subsequently are good and bad at. Highly recommended for technical and not-super-technical audiences alike. www.youtube.com/watch?v=7xTG...

0174

Reposted by Adam Ce

Dr Abeba Birhane @abeba.blacksky.app · 31/01/2025

queen did not mince a single word www.theguardian.com/commentisfre...

13887292

Reposted by Adam Ce

Zhenjun Zhao @ericzzj.bsky.social · 26/01/2025

Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass Jianing Yang, Alexander Sax, Kevin J. Liang, @mikaelhenaff.bsky.social, Hao Tang, Ang Cao, Joyce Chai, Franziska Meier, Matt Feiszli tl;dr: multi-view version of DUSt3R; over 1000 images arxiv.org/abs/2501.13928

2134

Reposted by Adam Ce

Rune Skovbo Johansen @runevision.bsky.social · 23/01/2025

New dithering method dropped I call it Surface-Stable Fractal Dithering and I've released it as open source along with this explainer video of how it works. Explainer video: www.youtube.com/watch?v=HPqG... Source repository: github.com/runevision/D... #gamedev #vfx

461591383

Reposted by Adam Ce

Anders Puck Nielsen @anderspucknielsen.dk · 22/01/2025

Was it sabotage or an accident when critical infrastructure was destroyed in the Baltic Sea by ships dragging their anchor across the seabed? I have collected some thoughts in this Q&A style blog post.

logicofwar.com

Sabotage or accidental anchor dragging in the Baltic Sea?

I have collected some answers to the basic questions raised by the recent discussion about whether the cable cutting in the Baltic Sea has been accidental or sabotage. This discussion was sparked by a...

2542889

Reposted by Adam Ce

Zhenjun Zhao @ericzzj.bsky.social · 22/01/2025

RDG-GS: Relative Depth Guidance with Gaussian Splatting for Real-time Sparse-View 3D Rendering Chenlu Zhan, Yufei Zhang, Yu Lin, Gaoang Wang, Hongwei Wang tl;dr: in title arxiv.org/abs/2501.11102

021

Reposted by Adam Ce

Christoph Peters @momentsingraphics.bsky.social · 12/01/2025

You cannot get physically-based rendering right without understanding radiometry. My new blog post explains it all, relying on familiar concepts from rendering algorithms as much as possible. Part 2 will come next week. momentsingraphics.de/Radiometry1B...

07822

Reposted by Adam Ce

nicebyte @nicebyte.bsky.social · 20/12/2024

gpu texture compression primer www.youtube.com/watch?v=3H-H...

youtube.com

GPU Texture Compression

YouTube video by Marmoset

05516

Reposted by Adam Ce

arxiv cs.CV @arxiv-cs-cv.bsky.social · 03/12/2024

Lihan Jiang, Kerui Ren, Mulin Yu, Linning Xu, Junting Dong, Tao Lu, Feng Zhao, Dahua Lin, Bo Dai Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes arxiv.org/abs/2412.01745

001

Adam Ce @adamcelarek.bsky.social · 03/12/2024

A Statistical Approach to Monte Carlo Denoising; TL;DR: Statistics made during path tracing including materials etc are used to achieve better denoising than neural network based solutions. No hallucinations, no problems if the training set is small, application to MIS. dl.acm.org/doi/10.1145/...

dl.acm.org

A Statistical Approach to Monte Carlo Denoising | SIGGRAPH Asia 2024 Conference Papers

000

Reposted by Adam Ce

Chris Offner @chrisoffner3d.bsky.social · 02/12/2024

Maybe I'm mistaken but I don't think you'd get to the quality of specular reflections of something like dorverbin.github.io/nerf-casting/ with a rasterization-based approach like 3DGS. The speed benefits of 3DGS are of course spectacular, but NeRF is still king w.r.t. image quality.

dorverbin.github.io

NeRF-Casting

121

Reposted by Adam Ce

Chris Offner @chrisoffner3d.bsky.social · 02/12/2024

Easier, yes, but also less "physically based." Here's @jonbarron.bsky.social on some of the recent work to use raytracing with Gaussian Splatting. youtu.be/h9vq_65eDas?...

youtu.be

Radiance Fields and The Future with Jon Barron

YouTube video by View Dependent

121

Reposted by Adam Ce

Jia-Bin Huang @jbhuang0604.bsky.social · 01/12/2024

3D Gaussian Splatting is awesome! BUT, the 3D Gaussian primitives often have difficulty reconstructing fine appearance details. 😩 Meet Textured Gaussians! ✋ Our RGBA Textured Gaussians enhance 3D scene appearance modeling. Learn more at textured-gaussians.github.io

58214

Reposted by Adam Ce

Chris Offner @chrisoffner3d.bsky.social · 28/11/2024

This podcast on "Radiance Fields and The Future" with @jonbarron.bsky.social is streaming right now! www.youtube.com/watch?v=h9vq...

youtube.com

Radiance Fields and The Future with Jon Barron

YouTube video by View Dependent

0295

Reposted by Adam Ce

Jan Held @janheld.bsky.social · 27/11/2024

Our paper "𝟑𝐃 𝐂𝐨𝐧𝐯𝐞𝐱 𝐒𝐩𝐥𝐚𝐭𝐭𝐢𝐧𝐠: 𝐑𝐚𝐝𝐢𝐚𝐧𝐜𝐞 𝐅𝐢𝐞𝐥𝐝 𝐑𝐞𝐧𝐝𝐞𝐫𝐢𝐧𝐠 𝐰𝐢𝐭𝐡 𝟑𝐃 𝐒𝐦𝐨𝐨𝐭𝐡 𝐂𝐨𝐧𝐯𝐞𝐱𝐞𝐬” is now available on Arxiv! 💻Project page for some cool visualizations: convexsplatting.github.io 📓 Paper: arxiv.org/abs/2411.14974

02613

Reposted by Adam Ce

Zhenjun Zhao @ericzzj.bsky.social · 27/11/2024

Geometry Field Splatting with Gaussian Surfels Kaiwen Jiang, Venkataram Sivaram, Cheng Peng, Ravi Ramamoorthi tl;dr: 2DGS/Gaussian surfels->geometry field->density field->volume splatting; rendered color->continuous function of surfels arxiv.org/abs/2411.17067

011

Adam Ce @adamcelarek.bsky.social · 26/11/2024

@tmaehara.bsky.social I like your arxive bots, and imo they would improve if the content would be changed to: 1. title 2. link 3. space 4. abstract (no authors to save space) would be even cooler if there would be screenshots of the paper, but i guess this is more work. what do you think?

110

Reposted by Adam Ce

arxiv cs.CV @arxiv-cs-cv.bsky.social · 26/11/2024

Xu Baixin, Hu Jiangbei, Li Jiaze, He Ying GSurf: 3D Reconstruction via Signed Distance Fields with Direct Gaussian Supervision arxiv.org/abs/2411.15723

001

Reposted by Adam Ce

arxiv cs.CV @arxiv-cs-cv.bsky.social · 26/11/2024

Yu Chen, Rolandos Alexandros Potamias, Evangelos Ververas, Jifei Song, Jiankang Deng, Gim Hee Lee ZeroGS: Training 3D Gaussian Splatting from Unposed Images arxiv.org/abs/2411.15779

001

Reposted by Adam Ce

François Fleuret @francois.fleuret.org · 26/11/2024

My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch. fleuret.org/dlc/ And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!) fleuret.org/lbdl/

461252247

Reposted by Adam Ce

Zhenjun Zhao @ericzzj.bsky.social · 25/11/2024

Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly Training for 4D Reconstruction Zhening Liu, Yingdong Hu, Xinjie Zhang, Jiawei Shao, Zehong Lin, Jun Zhang tl;dr: selective inheritance+dynamics-aware shift+error-guided densification arxiv.org/abs/2411.14847

062

Reposted by Adam Ce

Zhenjun Zhao @ericzzj.bsky.social · 25/11/2024

3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes Jan Held, Renaud Vandeghen, Abdullah Hamdi, Adrien Deliege, Anthony Cioppa, @silviogiancola.bsky.social, Andrea Vedaldi, Bernard Ghanem, Marc Van Droogenbroeck tl;dr: 3D smooth convexes->primitives arxiv.org/abs/2411.14974

1277

Reposted by Adam Ce

arxiv cs.CV @arxiv-cs-cv.bsky.social · 25/11/2024

Yuzhou Tang, Dejun Xu, Yongjie Hou, Zhenzhong Wang, Min Jiang NexusSplats: Efficient 3D Gaussian Splatting in the Wild arxiv.org/abs/2411.14514

001

Reposted by Adam Ce

Ishan Khatri @ishan.khatri.io · 23/11/2024

Also not to toot my own horn too much but we did this in ZeroFlow and we have a whole section about the significance of errors compared with the training variance over 3 training runs. It does cost compute but more people should do this!

Section of a paper describing the training variance of a method

051

Reposted by Adam Ce

David Picard @davidpicard.eurosky.social · 20/11/2024

🍏 New preprint alert! 🍏 PoM: Efficient Image and Video Generation with the Polynomial Mixer arxiv.org/abs/2411.12663 This is my latest "summer project" and it was so big I had to call in reinforcements (Thanks @nicolasdufour.bsky.social) TL;DR Transformers are for boomers, welcome to the future 🧵👇

arxiv.org

PoM: Efficient Image and Video Generation with the Polynomial Mixer

Diffusion models based on Multi-Head Attention (MHA) have become ubiquitous to generate high quality images and videos. However, encoding an image or a video as a sequence of patches results in costly...

19323

Reposted by Adam Ce

Matthias Niessner @niessner.bsky.social · 20/11/2024

Excited to announce the second iteration of our TUM AI Lecture series! We'll be having a lineup of top-notch speakers across areas in AI from both academia and industry. Talks will be streamed live and and remain available online - check out prev talks: niessner.github.io/TUM-AI-Lectu...

0387

Reposted by Adam Ce

Will Smith @willsmithvision.bsky.social · 18/11/2024

I recently gave a tutorial on the DUSt3R paper (web: dust3r.europe.naverlabs.com, paper: tinyurl.com/5t2ks575, code: github.com/naver/dust3r) in a research group meeting. In case you missed it, didn’t understand it or would like to hear some perspectives on why it’s such a cool idea, read on… 1/23

dust3r.europe.naverlabs.com

DUSt3R: Geometric 3D Vision Made Easy

67817

Reposted by Adam Ce

Rune Skovbo Johansen @runevision.bsky.social · 16/11/2024

I wanted to do a side-by-side comparison of my #procedural animation to hand-authored animations on some models I bought. This is so I can better study what I need to improve. When I got my comparison tool running for the first time, this is what I was greeted with! Step-height glitch I think. 😅

941907609

Reposted by Adam Ce

Kosta Derpanis @csprofkgd.bsky.social · 19/11/2024

My favourite example for model overfitting

1192

Reposted by Adam Ce

arxiv cs.CV @arxiv-cs-cv.bsky.social · 19/11/2024

Yifu Tao, Miguel \'Angel Mu\~noz-Ba\~n\'on, Lintong Zhang, Jiahao Wang, Lanke Frank Tarimo Fu, Maurice Fallon The Oxford Spires Dataset: Benchmarking Large-Scale LiDAR-Visual Localisation, Reconstruction and Radiance Field Methods arxiv.org/abs/2411.10546

001