Preprint of the day: Asim et al., "MEt3R: Measuring Multi-View Consistency in Generated Images" -- geometric-rl.mpi-inf.mpg.de/met3r/ Lots of diffusion-based solutions for novel-view synthesis recently, but how good are they? A metric to compare how "3D" they truly are.

The raw chain of thought from DeepSeek is fascinating, really reads like a human thinking out loud. Charming and strange.

I just pushed a new paper to arXiv. I realized that a lot of my previous work on robust losses and nerf-y things was dancing around something simpler: a slight tweak to the classic Box-Cox power transform that makes it much more useful and stable. It's this f(x, λ) here:

As one of the people who popularized the field of diffusion models, I am excited to share something that might be the “beginning of the end” of it. IMM has a single stable training stage, a single objective, and a single network — all are what make diffusion so popular today.

Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds! No expensive optimization needed, yet delivers SOTA results for: ✅ Camera Pose Estimation ✅ Multi-view Depth Estimation ✅ Dense

Thanks AK for sharing our ReCamMaster! ReCamMaster can re-capture existing videos with novel camera trajectories. Project page: jianhongbai.github.io/ReCamMaster/ Paper: huggingface.co/papers/2503.11…

⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)

🦣Easi3R: 4D Reconstruction Without Training! Limited 4D datasets? Take it easy. #Easi3R adapts #DUSt3R for 4D reconstruction by disentangling and repurposing its attention maps → make 4D reconstruction easier than ever! 🔗Page: easi3r.github.io

What's the difference between the oai and google image generators? Giving both of them the same image and prompt "generate this image" Gemini is essentially the identity function whereas oai changes content. Does this indicate continuous encoder for Gemini vs. VQVAE for oai?

After finishing ICCV reviews this year...

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy)

Interactive looong-context reasoning still has a long way to go. We need progress across all axes: more data, bigger model, and smarter architectures. ∞-THOR is just beginning: generate ∞-len trajectories, run agents online train with feedback and more! Let’s push the limits🚀

Poster #60 this afternoon, swing by!

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models Rundi Wu Ruiqi Gao Ben Poole Alex Trevithick ChangxiZheng Jon Barron Aleksander Holynski

If you’re at SIGGRAPH 2025 in Vancouver, join us Thu 2 PM for our talk “Generative Neural Materials”! We introduce a universal neural material model for bidirectional texture functions and a complementary generative pipeline. 1/2

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a

Come check out our workshop at the intersection of generative models and 3D reconstruction at #ICCV2025! 🏝️

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU. RTFM renders persistent and 3D consistent worlds, both real and imaginary. Try our demo of RTFM today!