Profile avatar
niessner.bsky.social
Professor for Visual Computing & Artificial Intelligence @TU Munich, Co-Founder @synthesiaIO https://niessnerlab.org/publications.html
36 posts 2,154 followers 60 following
Prolific Poster
Conversation Starter
Posts 33 Comments 11

๐Ÿ“ข๐Ÿ“ข ๐€๐ฏ๐š๐ญ๐Ÿ‘๐ซ ๐Ÿ“ข๐Ÿ“ข Avat3r creates high-quality 3D head avatars from just a few input images in a single forward pass with a new dynamic 3DGS reconstruction model. youtu.be/P3zNVx15gYs tobias-kirschstein.github.io/avat3r Great work by Tobias Kirschstein with J. Romero, A. Sevastopolsky, S. Saito.

submitted 11 hours ago โ€ข 0 comments

ETH starts a series of exciting guest talks on Robotics, Vision, and Controls this week. Tomorrow at 12:00 Zurich time, @adai.bsky.social from TU Munich will give a talk titled "From Quantity to Quality for 3D Perception." robotics-talks.com #robotics

submitted 10 days ago โ€ข 1 comment

Happening now! Join us if you want to more about #diffusion #stablediffusion #flux and many more :)

submitted 11 days ago โ€ข 1 comment

Tomorrow in our TUM AI - Lecture Series with none other than Robin Rombach, CEO Black Forest Labs. He'll talk about "๐…๐‹๐”๐—: Flow Matching for Content Creation at Scale". Live stream: youtube.com/live/nrKKLJX... 6pm GMT+1 / 9am PST (Mon Feb 17rd)

submitted 12 days ago โ€ข 1 comment

(1/n) ๐Ÿ“ข๐Ÿ“ข ๐๐ž๐‘๐’๐ž๐ฆ๐›๐ฅ๐ž ๐ฏ๐Ÿ ๐ƒ๐š๐ญ๐š๐ฌ๐ž๐ญ ๐‘๐ž๐ฅ๐ž๐š๐ฌ๐ž ๐Ÿ“ข๐Ÿ“ข Head captures of 7.1MP from 16 cameras at 73fps: * More recordings (425 people) * Better color calibration * Convenient download scripts github.com/tobias-kirsc...

submitted 17 days ago โ€ข 1 comment

Excited to bring back the 2nd ScanNet++ Novel View Synthesis and 3D Semantic Understanding Challenge at #CVPR 2025! Submit to our new benchmark, now with over 1000 high-fidelity scans of real-world scenes: kaldir.vc.in.tum.de/scannetpp/ Check it out: kaldir.vc.in.tum.de/scannetpp/cv...

submitted 22 days ago โ€ข 1 comment

Happening now - join us if you like 3D Gaussian Splatting!!!

submitted 25 days ago โ€ข 0 comments

Tomorrow in our TUM AI - Lecture Series with none other than George Drettakis. He'll talk about "๐“๐ก๐ž ๐Ÿ‘๐ƒ ๐†๐š๐ฎ๐ฌ๐ฌ๐ข๐š๐ง ๐’๐ฉ๐ฅ๐š๐ญ๐ญ๐ข๐ง๐  ๐€๐๐ฏ๐ž๐ง๐ญ๐ฎ๐ซ๐ž: ๐๐š๐ฌ๐ญ, ๐๐ซ๐ž๐ฌ๐ž๐ง๐ญ, ๐…๐ฎ๐ญ๐ฎ๐ซ๐ž". Live stream: youtube.com/live/DjOqkVI... 5pm GMT+1 / 8am PST (Mon Feb 3rd)

submitted 26 days ago โ€ข 0 comments

๐Ÿ“ข ScanNet++ v2 Benchmark Release! ๐Ÿ† Test your state-of-the-art models on: ๐Ÿ”น Novel View Synthesis ๐Ÿ“ธโžก๏ธ๐Ÿ–ผ๏ธ ๐Ÿ”น 3D Semantic & Instance Segmentation ๐Ÿค–๐Ÿ”๐Ÿ•ถ๏ธ Shoutout to @awhiteguitar.bsky.social & Yueh-Cheng Liu for their incredible work๐Ÿ‘ ๐Ÿš€Check it out: kaldir.vc.in.tum.de/scannetpp/

submitted 28 days ago โ€ข 0 comments

๐Ÿš€ ๐„๐ฎ๐ซ๐จ๐ ๐ซ๐š๐ฉ๐ก๐ข๐œ๐ฌ ๐Ÿ๐ŸŽ๐Ÿ๐Ÿ“ - Registration is Open! ๐Ÿ’ป๐ŸŽจ Join us in London, May 12-16, 2025, for one of the leading Computer Graphics conferences in the world and an incredible week of research innovation! ๐Ÿ”— Register now: eg25.cs.ucl.ac.uk/main/registr...

submitted 29 days ago โ€ข 1 comment

With DeepSeek, opinions are shifting from "winning in AI needs infinite compute" to "all cutting-edge models are cheap and free". It's somewhat obvious that brute-force compute was a bad idea, while at the same time, training big models still takes significant resources.

submitted 29 days ago โ€ข 1 comment

Winter is coming on our TUM campus in Garching :)

submitted 37 days ago โ€ข 0 comments

Merry Christmas & Happy Holidays๐ŸŽ…๐ŸŽ„๐Ÿ•ฏ๏ธ May your tokens generate well, noise diffuse smoothly, splats shine with radiance, and your GPUs burn bright - but not out! Splat-acular holidays everyone!

submitted 66 days ago โ€ข 1 comment

Excited to announce ScanNet++ v2!๐ŸŽ‰ @awhiteguitar.bsky.social & Yueh-Cheng Liu have been working tirelessly to bring: ๐Ÿ”น1006 high-fidelity 3D scans ๐Ÿ”น+ DSLR & iPhone captures ๐Ÿ”น+ rich semantics Elevating 3D scene understanding to the next level!๐Ÿš€ w/ @niessner.bsky.social kaldir.vc.in.tum.de/scannetpp

submitted 70 days ago โ€ข 1 comment

Reviewers were just assigned and someone already submitted a #CVPR review - commendable! Don't wait till the last minute :)

submitted 72 days ago โ€ข 0 comments

(1/2) ๐Ÿ“ข๐Ÿ“ข๐†๐€๐…: ๐†๐š๐ฎ๐ฌ๐ฌ๐ข๐š๐ง ๐€๐ฏ๐š๐ญ๐š๐ซ ๐‘๐ž๐œ๐จ๐ง๐ฌ๐ญ๐ซ๐ฎ๐œ๐ญ๐ข๐จ๐ง ๐Ÿ๐ซ๐จ๐ฆ ๐Œ๐จ๐ง๐จ๐œ๐ฎ๐ฅ๐š๐ซ ๐•๐ข๐๐ž๐จ๐ฌ ๐ฏ๐ข๐š ๐Œ๐ฎ๐ฅ๐ญ๐ข-๐ฏ๐ข๐ž๐ฐ ๐ƒ๐ข๐Ÿ๐Ÿ๐ฎ๐ฌ๐ข๐จ๐ง๐Ÿ“ข๐Ÿ“ข We reconstruct animatable Gaussian head avatars from monocular videos captured by commodity devices such as smartphones.

submitted 73 days ago โ€ข 1 comment

Super happy to present our #NeurIPS paper ๐‚๐จ๐ก๐ž๐ซ๐ž๐ง๐ญ ๐Ÿ‘๐ƒ ๐’๐œ๐ž๐ง๐ž ๐ƒ๐ข๐Ÿ๐Ÿ๐ฎ๐ฌ๐ข๐จ๐ง ๐…๐ซ๐จ๐ฆ ๐š ๐’๐ข๐ง๐ ๐ฅ๐ž ๐‘๐†๐ ๐ˆ๐ฆ๐š๐ ๐ž in Vancouver. Come to our poster #2804 on Wednesday 11am - 2pm in East Exhibit Hall, if you want to learn more about 3D Scene Diffusion! See you tomorrow! Project Page: manuel-dahnert.com/research/sce...

submitted 79 days ago โ€ข 1 comment

๐Ÿ“ข ๐๐ซ๐„๐๐ข๐ญ๐จ๐ซ๐Ÿ‘๐ƒ: ๐…๐š๐ฌ๐ญ ๐š๐ง๐ ๐๐ซ๐ž๐œ๐ข๐ฌ๐ž ๐Ÿ‘๐ƒ ๐’๐ก๐š๐ฉ๐ž ๐„๐๐ข๐ญ๐ข๐ง๐  ๐Ÿ“ข We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is.

submitted 80 days ago โ€ข 1 comment

๐Ÿ“ขDNF: Generating 4D animations with dictionary-based neural fields! Xinyi Zhang presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency. xzhang-t.github.io/project/DNF/

submitted 81 days ago โ€ข 0 comments

My students are also happy! #ERC

submitted 87 days ago โ€ข 0 comments

(1/2) Our proposal ๐†๐ž๐ง๐Ÿ‘๐ƒ: ๐‹๐ž๐š๐ซ๐ง๐ข๐ง๐  ๐ญ๐จ ๐‚๐ซ๐ž๐š๐ญ๐ž ๐•๐ข๐ซ๐ญ๐ฎ๐š๐ฅ ๐–๐จ๐ซ๐ฅ๐๐ฌ was awarded the #ERC Consolidator Grant! The grant comes with 2.75M โ‚ฌ in funding and will facilitate cutting-edge research on generative AI methods for 3D content creation.

submitted 87 days ago โ€ข 5 comments

Presenting super exciting papers at SIGGRAPH Asia: L3DG: Latent 3D Gaussian Diffusion lnkd.in/edAiSaqZ GGHead: Fast and Generalizable 3D Gaussian Heads lnkd.in/erKhanNC NPGA: Neural Parametric Gaussian Avatars lnkd.in/ePwA6mtP Work by B. Rรถssle, S. Giebenhain, T. Kirschstein

submitted 88 days ago โ€ข 0 comments

(1/3) ๐Ÿ“ข๐Ÿ“ข ๐†๐š๐ฎ๐ฌ๐ฌ๐ข๐š๐ง๐’๐ฉ๐ž๐ž๐œ๐ก: Audio-Driven Gaussian Avatars ๐Ÿ“ข๐Ÿ“ข We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. shivangi-aneja.github.io/projects/gau... youtu.be/2VqYoFlYcwQ

submitted 88 days ago โ€ข 1 comment

Kicking off our TUM AI - Lecture Series tomorrow with none other than Jiaming Song, CSO @LumaLabsAI. He'll be talking about "Dream Machine: Emergent Capabilities from Video Foundation Models". Live stream: youtu.be/oilWwsXZamA 7pm GMT+1 / 10am PST (Mon Dec 2nd)

submitted 89 days ago โ€ข 1 comment

(1/4) I will present GGHead next week at SIGGRAPH Asia in Tokyo! Swing by in the Gaussian Humans session if you are interested. Also, we have released the training code now ๐ŸŽ‰ Check it out: github.com/tobias-kirsc...

submitted 92 days ago โ€ข 1 comment

Christmas market in #Munich is open๐ŸŽ…๐ŸŽ„ On the photo you can see the city council with its famous glockenspiel and stunning appearance - perfect time of the year to enjoy some Glรผhwein :)

submitted 92 days ago โ€ข 0 comments

(1/2) Daytrip to #Neuschwanstein - the famous fairytale castle built by King Ludwig II of Bavaria ๐Ÿฐ It offers stunning views overlooking the Alpsee & Schwansee at the foot of the Alps - quite remarkable! en.wikipedia.org/wiki/Neuschw...

submitted 95 days ago โ€ข 1 comment

Official promotion to ๐…๐ฎ๐ฅ๐ฅ ๐๐ซ๐จ๐Ÿ๐ž๐ฌ๐ฌ๐จ๐ซ ๐Ÿฅณ๐Ÿฅณ๐Ÿฅณ Thanks so much to everyone who has been with me on this exciting journey, in particular my amazing PhD students, PostDocs, collaborators, every other supporter! Let's see what's next - just getting started :)

submitted 98 days ago โ€ข 2 comments

Want to work on cutting-edge research in #AI? We have several ๐๐ก๐ƒ & ๐๐จ๐ฌ๐ญ๐ƒ๐จ๐œ ๐จ๐ฉ๐ž๐ง๐ข๐ง๐ ๐ฌ in our Visual Computing & AI Lab in Munich! Topics have a strong focus on GenAI, including 3DGs, NeRFs, Diffusion Models, LLMs, etc. Share & apply :) application.vc.in.tum.de

submitted 99 days ago โ€ข 1 comment

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...

submitted 100 days ago โ€ข 0 comments

Good overview of notable AI models wrt training compute: epoch.ai/data/notable... Can sort by all kinds of criteria such as model size, compute budget, etc. The largest models take between 1e24 to 1e26 FLOPs. Obviously, scale of models has exploded in the recent years :)

submitted 101 days ago โ€ข 0 comments

Success of social media ultimately depends on the quality of content and who sees it. When platforms start out, they tend to do a pretty good job - they connect people with their interests. Major issues arise when trying squeeze out engagement with all sorts of garbage...

submitted 101 days ago โ€ข 3 comments

Finally the ๐Œ๐ž๐ฌ๐ก๐†๐๐“ code is online: github.com/audi/MeshGPT Also shoutout to the recent mesh generators such as MeshAnything, MeshXL, EdgeRunner, LLaMA-Mesh, and many more. It's a super exciting research area - 3D meshes for the win!!!

submitted 102 days ago โ€ข 2 comments