Guillaume Astruc @g_astruc

2nd Year PhD Student from Imagine-ENPC/IGN/CNES Joined July 2022

Tweets

38
Followers

70
Following

63
Likes

169

Antoine Guédon @antoine_guedon

3 weeks ago

1/n🚀Gaussians > Differentiable function > Mesh? Check out our new work: MILo: Mesh-In-the-Loop Gaussian Splatting! 🎉Accepted to SIGGRAPH Asia 2025 (TOG) MILo is a novel differentiable framework that extracts meshes directly from Gaussian parameters during training. 🧵👇

6 61 337 23K 186

Download Image

Guillaume Astruc @g_astruc

a month ago

Super interesting to see pure SSL outperforms text alignement on a super competitive but text-aligned suited task 🤯

Nicolas DUFOUR @nico_dufour

a month ago

Super interesting to see pure SSL outperforms text alignement on a super competitive but text-aligned suited task 🤯

3 34 288 35K 160

Download Image

0 0 3 136 0

Guillaume Astruc @g_astruc

4 months ago

🛰️ At #CVPR2025 presenting "AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities" - Saturday afternoon, Poster 355! If you're here and want to discuss geolocation or geospatial foundation models, let's connect!

1 3 15 1K 2

Nicolas DUFOUR @nico_dufour

4 months ago

I will be at #CVPR2025 this week in Nashville. I will be presenting our paper "Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation". We tackle geolocalization as a generative task allowing for SOTA performance and more interpretable predictions.

1 5 9 361 0

Download Image

Ryan @RyanBoustany_

4 months ago

📢New preprint “When majority rules, minority loses: bias amplification of gradient descent” We often blame biased data but training also amplifies biases. Our paper explores how ML algorithms favor stereotypes at the expense of minority groups. ➡️arxiv.org/abs/2505.13122 (1/3)

1 2 5 589 2

Guillaume Astruc @g_astruc

5 months ago

We've added new experiments demonstrating robust generalization capabilities! Notably, AnySat shows strong performance on HLS Burn Scars - a sensor never seen during pretraining! 🔥🛰️ Check it out: 📄 Paper: arxiv.org/abs/2412.14123 🌐 Project: gastruc.github.io/anysat

Loic Landrieu @loiclandrieu

5 months ago

0 0 11 335 1

0 1 9 220 0

Download Image

Lucas Ventura @Lucas__Ventura

6 months ago

Introducing Chapter-Llama [#CVPR2025], a framework for 𝐯𝐢𝐝𝐞𝐨 𝐜𝐡𝐚𝐩𝐭𝐞𝐫𝐢𝐧𝐠 using Large Language Models! 🎬🦙 Check it out: 📄 Paper: arxiv.org/abs/2504.00072 🔗 Project: imagine.enpc.fr/~lucas.ventura… 💻 Code: github.com/lucas-ventura/… 🤗 Demo: huggingface.co/spaces/lucas-v…

4 39 201 16K 107

Download Video

Antoine Guédon @antoine_guedon

6 months ago

💻We've released the code for our #CVPR2025 paper MAtCha! 🍵MAtCha reconstructs sharp, accurate and scalable meshes of both foreground AND background from just a few unposed images (eg 3 to 10 images)... ...While also working with dense-view datasets (hundreds of images)!

6 83 534 50K 427

Download Image

Thibaut Loiseau @thibaut_loiseau

7 months ago

1/13 🐊 Introducing our latest work on improving relative camera pose regression with a novel pre-training approach Alligat0R (arxiv.org/abs/2503.07561)! @GBourmaud @VincentLepetit2

2 8 12 631 3

Download Image

Thibaut Loiseau @thibaut_loiseau

7 months ago

🧩Excited to share our paper "RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges" arxiv.org/abs/2502.19955 accepted to #CVPR2025! We created a benchmark that systematically evaluates image matching methods across well-defined geometric difficulty levels.

1 4 20 786 1

Download Image

Nayel Bettache @NayelBettache

9 months ago

🎉 Excited to share my first single-author preprint. Proud of this contribution. I would be grateful for any feedback or thoughts. 🙌

arXiv math.ST Statistics Theory @mathSTb

9 months ago

🎉 Excited to share my first single-author preprint. Proud of this contribution. I would be grateful for any feedback or thoughts. 🙌

0 4 16 4K 4

0 2 8 1K 2

Robin Cole @robmarkcole

9 months ago

AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities

1 6 45 5K 23

Isaac Corley @isaaccorley_

9 months ago

AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities @g_astruc @NicaoGr Clement Mallet @loiclandrieu tldr: pretrains a multisensor & multimodal joint embedding network on GeoPlex dataset. achieves SOTA on a diverse set of time-series EO benchmarks

1 9 86 10K 54

Download Image

Antoine Guédon @antoine_guedon

10 months ago

⚠️Reconstructing sharp 3D meshes from a few unposed images is a hard and ambiguous problem. ☑️With MAtCha, we leverage a pretrained depth model to recover sharp meshes from sparse views including both foreground and background, within mins!🧵 🌐Webpage: anttwo.github.io/matcha/