Tessera
Folgen

Valentin Deschaintre

@vdeschaintre.bsky.social

Doing research at Adobe in Computer Graphics/Vision/ML on appearance & content authoring and generation. I also like photography, and baking, but I try to keep it under control! https://valentin.deschaintre.fr

120 Posts1128 Follower227 Folgt
Annie Gottfried Cohen@annsplaining.bsky.social · 8mo ago

I asked my husband if there is a French equivalent of "sticks and stones will break my bones" and he gave me "the toad's drool doesn't reach the white dove" and "the train of your insults is rolling on the rails of my indifference" and now I would like both of these on a t-shirt

Alban Gauthier@albangauthier.bsky.social · 9mo ago

The implementation of our paper called "An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes" is now available at: github.com/graphdeco-in... Project Page: repo-sam.inria.fr/nerphys/svbr...

GitHub - graphdeco-inria/svbrdf-evaluation: Official implementation of the article "An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes"

Official implementation of the article "An evaluation of SVBRDF Prediction from Generative Image Models for Appearance Modeling of 3D Scenes" - graphdeco-inria/svbrdf-evaluation

github.com

Valentin Deschaintre@vdeschaintre.bsky.social · 12mo ago

I will be presenting in the 10.30 session in room 208-209. I will share thoughts about implicit/generative and explicit appearance representations. See you there if that sounds interesting!

Valentin Deschaintre@vdeschaintre.bsky.social · 12mo ago

🧑‍🎓I have the pleasure to present at the Best of Eurographics session at #SIGGRAPH2025 next week! I’ll be looking back at our work on appearance authoring, editing & understanding — come by and say hi! 🔗 s2025.conference-schedule.org/presentation...

Iliyan Georgiev@iliyangeo.bsky.social · last yr.

Editing appearance, geometry, lighting with precision is easy with a 3D scene representation. But it's so much more difficult with just an image or photograph. Enter IntrinsicEdit: Precise generative image manipulation in intrinsic space (SIGGRAPH 2025)! intrinsic-edit.github.io

IntrinsicEdit: Precise generative image manipulation in intrinsic space

We present a powerful generative editing workflow built on the RGB-X diffusion framework, enabling pixel-precise, semantic image manipulation across tasks like relighting, color adjustment, and object...

intrinsic-edit.github.io

Valentin Deschaintre@vdeschaintre.bsky.social · last yr.

⭐ Image editing without paired data, delivering on the promise of RGB<->X! Edit in Intrinsic space, get back your image with the desired modification! The method is quite fun too, conditional token optimization and noise inversion.

Iliyan Georgiev@iliyangeo.bsky.social · last yr.

Editing appearance, geometry, lighting with precision is easy with a 3D scene representation. But it's so much more difficult with just an image or photograph. Enter IntrinsicEdit: Precise generative image manipulation in intrinsic space (SIGGRAPH 2025)! intrinsic-edit.github.io

Valentin Deschaintre@vdeschaintre.bsky.social · last yr.

I was very honoured to receive one of the two Eurographics Young Researcher Award 2025 yesterday! This is the combination of the work of many people, mentors, collaborators, students, friends who trusted me and taught me so much along the way!

BildBildBildBild
Ruben Wiersma@rubenwiersma.nl · last yr.

Recent progress in multi-view 3D object capture is stunning! But is there a limit? In our upcoming #SIGGRAPH2025 paper "Uncertainty for SVBRDF Acquisition using Frequency Analysis," we show how to answer this question for material estimation. 1/6

The figure illustrates a pipeline for estimating uncertainty and spatially-varying material properties of a plush dinosaur toy. On the left, a rendered model shows the input: incoming lighting, the BRDF, and outgoing lighting from multi-view captures. Three plots in the center display spherical harmonics power spectra for incoming lighting, BRDF, and outgoing lighting. Right side: first, a colored uncertainty map (entropy) over the dinosaur surface is shown, computed within 0.5 milliseconds. Then, three images show estimated base color, roughness, and metallicity maps, computed in about 3 seconds.
Valentin Deschaintre@vdeschaintre.bsky.social · last yr.

This was a blast to work on, understanding the signal available to estimate the uncertainty in your material recovery! And it's fast enough to inform your future capture steps in real time!

Ruben Wiersma@rubenwiersma.nl · last yr.

Recent progress in multi-view 3D object capture is stunning! But is there a limit? In our upcoming #SIGGRAPH2025 paper "Uncertainty for SVBRDF Acquisition using Frequency Analysis," we show how to answer this question for material estimation. 1/6

The figure illustrates a pipeline for estimating uncertainty and spatially-varying material properties of a plush dinosaur toy. On the left, a rendered model shows the input: incoming lighting, the BRDF, and outgoing lighting from multi-view captures. Three plots in the center display spherical harmonics power spectra for incoming lighting, BRDF, and outgoing lighting. Right side: first, a colored uncertainty map (entropy) over the dinosaur surface is shown, computed within 0.5 milliseconds. Then, three images show estimated base color, roughness, and metallicity maps, computed in about 3 seconds.
Antoine Guédon@antoine-guedon.bsky.social · last yr.

💻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)!

BildBildBildBild
Valentin Deschaintre@vdeschaintre.bsky.social · last yr.

Reading quite a few colleagues/friends mention that their SIGGRAPH summary seems generated by AI. If you are the point where you are using ChatGPT to generate review summaries for paper on which people worked hard, maybe reject the IPC invitation next time, you clearly don't have the time for it...