@thibaultgroueix.bsky.social
Given N image generation jobs, can we do better than N calls to text-to-image ? @daledecatur.bsky.social proposes to share compute across a batch of jobs, achieving higher efficiency at similar quality.
Check out our #ICCV2025 poster #153 today during Poster Session #4 from 2:45-4:45 HST!
Check out our #ICCV2025 poster #153 today during Poster Session #4 from 2:45-4:45 HST!
Excited to share our #ICCV2025 work Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets!
Our method generates large sets of images using significantly less compute than standard diffusion.
📎https://ddecatur.github.io/hierarchical-diffusion/
1/
Our method generates large sets of images using significantly less compute than standard diffusion.
📎https://ddecatur.github.io/hierarchical-diffusion/
1/
October 22, 2025 at 8:42 PM
Given N image generation jobs, can we do better than N calls to text-to-image ? @daledecatur.bsky.social proposes to share compute across a batch of jobs, achieving higher efficiency at similar quality.
Check out our #ICCV2025 poster #153 today during Poster Session #4 from 2:45-4:45 HST!
Check out our #ICCV2025 poster #153 today during Poster Session #4 from 2:45-4:45 HST!
CV folks, we knew it was bound to come. For at least 10 years if not more (I remember giving an interview about that in a journal at least 10 years ago). Now, the question is what do we do about it? What could CV do to solve a problem it has created?
Russia deploys AI-powered drones that autonomously select targets — including civilians — posing a direct threat to the population, reports Defense Express. These new drones fly up to 100 km without operators, navigate via terrain imaging (no GPS), evading electronic warfare.
May 22, 2025 at 2:38 AM
Man-made objects are often repeated in urban scene. 🎳 Can we leverage these repetitions to improve 3D reconstruction 📷? Exploration led by the titan Nicolas Violante Grezzi 👇🧵
Excited to share our paper, "Splat and Replace: 3D Reconstruction with Repetitive Elements", which I'll be presenting at #SIGGRAPH2025!
Project page: repo-sam.inria.fr/nerphys/spla...
1/3
Project page: repo-sam.inria.fr/nerphys/spla...
1/3
May 13, 2025 at 3:38 PM
Man-made objects are often repeated in urban scene. 🎳 Can we leverage these repetitions to improve 3D reconstruction 📷? Exploration led by the titan Nicolas Violante Grezzi 👇🧵
Great opportunity! This is a dream team, and they are located 20 minutes from Paris.
We're hiring! IMAGINE @ École des Ponts (Paris area) is opening a 4-year "CV for X" researcher position:
– competitive salary
– no teaching load
– starting pkg ≈ 2 PhDs
– goal: impactful core AI + X (climate, biodiversity, robotics...)
Apply by May 31: imagine-lab.enpc.fr/wp-content/u...
– competitive salary
– no teaching load
– starting pkg ≈ 2 PhDs
– goal: impactful core AI + X (climate, biodiversity, robotics...)
Apply by May 31: imagine-lab.enpc.fr/wp-content/u...
April 25, 2025 at 4:56 PM
Great opportunity! This is a dream team, and they are located 20 minutes from Paris.
OpenAi Ghibli style + the new FramePack (ControlNet team). I am very impressed by this model, and it was super easy to run. Is it a commoditization moment for video GenAi?
April 18, 2025 at 12:05 AM
OpenAi Ghibli style + the new FramePack (ControlNet team). I am very impressed by this model, and it was super easy to run. Is it a commoditization moment for video GenAi?
Would anyone know the best current code for human keypoint estimation from a video of a single human?
March 5, 2025 at 1:58 AM
Would anyone know the best current code for human keypoint estimation from a video of a single human?
Proposal: Reviewers who have not given any sign-of-life to the AC get an automatic flag on the rebuttal of the papers they submitted, to be considered at the discretion of the reviewers of those papers.
January 17, 2025 at 12:28 AM
Proposal: Reviewers who have not given any sign-of-life to the AC get an automatic flag on the rebuttal of the papers they submitted, to be considered at the discretion of the reviewers of those papers.
Best of 2024 ?
Movies : Perfect Days (runner-up Anora)
Series: three-body problem
Animated series: Arcane
Research paper: Dust3r
Manga: Oshi no ko
What about you?
Movies : Perfect Days (runner-up Anora)
Series: three-body problem
Animated series: Arcane
Research paper: Dust3r
Manga: Oshi no ko
What about you?
December 28, 2024 at 12:07 PM
Best of 2024 ?
Movies : Perfect Days (runner-up Anora)
Series: three-body problem
Animated series: Arcane
Research paper: Dust3r
Manga: Oshi no ko
What about you?
Movies : Perfect Days (runner-up Anora)
Series: three-body problem
Animated series: Arcane
Research paper: Dust3r
Manga: Oshi no ko
What about you?
From a few user clicks to 3D material segmentation - in seconds ⌛. It's exciting to see so many pieces in 3D generation and analysis starting to work reliably and fast ! Super nice work from Michael and team (mfischer-ucl.github.io)
🎓 We introduce SAMa! A material selection and segmentation model on 3D models in any format (3DGS, NeRF, Mesh).
Given a user click, we propose to select all regions on an objects with the same material. We can also do segmentation in under a minute: mfischer-ucl.github.io/sama/
Given a user click, we propose to select all regions on an objects with the same material. We can also do segmentation in under a minute: mfischer-ucl.github.io/sama/
December 10, 2024 at 1:09 AM
From a few user clicks to 3D material segmentation - in seconds ⌛. It's exciting to see so many pieces in 3D generation and analysis starting to work reliably and fast ! Super nice work from Michael and team (mfischer-ucl.github.io)
🌟 Text-to-3D is awesome ! But how do we iterate on the generated 3D model, to get just the right result? Do we tweak the prompt endlessly? Revert to traditional 3D modeling techniques?
We propose a solution to "3D inpainting” 🤩🎨
Project: amirbarda.github.io/Instant3dit....
A thread. 🧵 1/
We propose a solution to "3D inpainting” 🤩🎨
Project: amirbarda.github.io/Instant3dit....
A thread. 🧵 1/
December 4, 2024 at 1:49 AM
🌟 Text-to-3D is awesome ! But how do we iterate on the generated 3D model, to get just the right result? Do we tweak the prompt endlessly? Revert to traditional 3D modeling techniques?
We propose a solution to "3D inpainting” 🤩🎨
Project: amirbarda.github.io/Instant3dit....
A thread. 🧵 1/
We propose a solution to "3D inpainting” 🤩🎨
Project: amirbarda.github.io/Instant3dit....
A thread. 🧵 1/