Excited to share our work, ObjectCarver! Given multiview images and click points on one image, ObjectCarver decomposes scenes into separate objects, providing high-quality 3D surfaces while handling occlusion and close-contact objects. (1/6) website: objectcarver.github.io

I'm a big fan of work on visual discovery, and this work on using diffusion models for data mining is really cool!

Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little! Introducing "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"—a fully transformer-based approach that enables scalable,

Extreme Rotation Estimation in the Wild Hana Bezalel, Dotan Ankri, Ruojin Cai Hadar Averbuch-Elor tl;dr: MegaDepth/Scenes subset with small/large/no overlap image pairs, the task is R prediction arxiv.org/abs/2411.07096

We've released our paper "Generating 3D-Consistent Videos from Unposed Internet Photos"! Video models like Luma generate pretty videos, but sometimes struggle with 3D consistency. We can do better by scaling them with 3D-aware objectives. 1/N page: genechou.com/kfcw

#3DV2025AMA Third guest on the Ask Me Anything series: Noah Snavely Noah Snavely from Cornell & Google DeepMind! 🌟 🕒 You have now 24 HOURS to ask him anything — drop your questions in the comments below! We have also the AMA happening on Bluesky: bsky.app/profile/3dvcon…

Introducing MegaSaM! 🎥 Accurate, fast, & robust structure + camera estimation from casual monocular videos of dynamic scenes! MegaSaM outputs camera parameters and consistent video depth, scaling to long videos with unconstrained camera paths and complex scene dynamics!

Introducing Doppelgangers++! 🚀 An enhanced pairwise image classifier that tackles visual aliasing (doppelgangers) to improve 3D reconstruction accuracy across diverse, real-world scenes. 🌍✨ 🔗Project page: bit.ly/3VAPMJc. Code is also available.

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

I can’t attend the #NeurIPS conference this year, but Yuanbo Xiangli will present Neural Gaffer in person. Drop by our poster at West Ballroom A-D #7001 if you are interested! Time: Fri 13 Dec 4:30 p.m. — 7:30 p.m.

🤔Can Generative Video Models Help Pose Estimation? ✅Yes! We find that generative video models can hallucinate plausible intermediate frames that provide useful context for pose estimators (e.g. DUSt3R), especially for images with little to no overlap. 🔗 inter-pose.github.io

These days, I only get around to trying every third or fourth social media site that comes along. The one I really like right now is Bluesky. It's a bit hard to describe, kind of like a new-fangled Usenet, but I highly recommend it! snavely.bsky.social

Really cool work from Hadar Averbuch-Elor and co!

Our paper LVSM has been accepted as an oral presentation at #ICLR2025! See you in Singapore! We’ve just released the code and checkpoints—check it out here: github.com/haian-jin/LVSM.🚀

Curious about how cities have changed in the past decade? We use MLLMs to analyse 40 million Street View images to answer this. Do you know that "juice shops became a thing in NYC" and "miles of overpasses were painted BLUE in SF"? More at→boyangdeng.com/visual-chronic… (vid ↓ w/ 🔊)

We have released the Stereo4D dataset! Explore the real-world dynamic 3D tracks: github.com/Stereo4d/stere…

1/6 🔍➡️ How to transform standard videos into immersive 360° panoramas? We've designed a new AI system for video-to-360° panorama generation! Our key insight: large-scale data is crucial for robust panoramic synthesis across diverse scenes.

Think LMMs can reason like a 3-year-old? Think again! Our Kid-Inspired Visual Analogies benchmark reveals where young children still win: ey242.github.io/kiva.github.io/ Catch our #ICLR2025 poster today to see where models still fall short! Thurs. April 24 3-5:30 pm Halls 3 + 2B #312

Excited to attend #ICLR2025 in person this year! I’ll be presenting two papers: 1. LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias 🔹 Oral Presentation: Session 3C (Garnet 216-218) — Apr 25 (Fri), 11:06–11:18 a.m. 🔹 Poster: Hall 3 + Hall 2B, Poster #593 — Apr

MegaSaM got an award! Big congrats to the team!!!!! 🥳🥳🎉🎉 Zhengqi Li, Richard, Forrester Cole, Linyi Jin, Qianqian Wang, Vickie Angjoo Kanazawa, Noah Snavely