北アルプスで最も美しい火山湖「みくりが池」の室堂周辺を丸ごと3D化し、アバターで歩けるようにしました。 どなたでもArrival Spaceからご覧いただけます。 URL: arrival.space/murodou_mikuri…

We've released the ICCV 2025 Report! hirokatsukataoka.net/temp/pr… Compiled during ICCV in collaboration with LIMIT.Lab, cvpaper.challenge, and Visual Geometry Group (VGG), this report offers meta insights into the trends and tendencies observed at this year's conference. #ICCV2025

When I started working in python, I got lazy with “single assignment”, and I need to nudge myself about it. You should strive to never reassign or update a variable outside of true iterative calculations in loops. Having all the intermediate calculations still available is helpful in the debugger, and it avoids problems where you move a block of code and it silently uses a version of the variable that wasn’t what it originally had. In C/C++, making almost every variable const at initialization is good practice. I wish it was the default, and mutable was a keyword.

The hot topic at #ICCV2025 was World Models. They come in different flavors — (interactive) video models, neural simulators, reconstruction models, etc. — but the overarching goal is clear: Generative AI that predict and simulate how the real world works.

The scene at Bobby Dodd Stadium at the start of the second quarter

How does our brain excel at complex object recognition, yet get fooled by simple illusory contours? What unifying principle governs all Gestalt laws of perceptual organization? We may have an answer: integration of learned priors through feedback. New paper with Ken Miller! 🧵

筑波の航空写真に，点群地図を透過させてみたが，ほぼあってる．GLIMすごい

🏆 Excited to share that BrickGPT (avalovelace1.github.io/Brick…) received the ICCV Best Paper Award! Our first author, @AvaLovelace0, will present it from 1:30 to 1:45 p.m. today in Exhibit Hall III. Huge thanks to all the co-authors @RuixuanLiu_ @RamananDeva @ChangliuL @junyanz89

Simulation drives robotics progress, but how do we close the reality gap? Introducing GaussGym: an open-source framework for learning locomotion from pixels with ultra-fast parallelized photorealistic rendering across >4,000 iPhone, GrandTour, ARKit, and Veo scenes! Thread 🧵

GPT-5-Codex, optimized for agentic coding, is rolling out to @code now! Try it out and let us know what you think. github.blog/changelog/2025-0…

InstantSfM: Fully Sparse and Parallel Structure-from-Motion TLDR: InstantSfM is a fully sparse and parallel Structure-from-Motion pipeline. It leverages GPU acceleration to achieve up to 40× speedup over traditional methods like COLMAP, while maintaining or improving reconstruction accuracy across diverse datasets. Contributions: • We extend sparse-aware bundle adjustment techniques to global positioning, introducing a complete global SfM system in PyTorch. • We demonstrate state-of-the-art efficiency while achieving comparable accuracy to both traditional, well-established SfM pipelines and learning-based methods. • We incorporate depth prior into the optimization so that camera parameters and 3D point clouds are recovered at metric scale. InstantSfM significantly outperforms compared methods on several datasets.

𝗗𝗟𝗥 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵𝗲𝗿𝘀 𝗴𝗮𝘃𝗲 𝗮 𝗿𝗼𝗯𝗼𝘁𝗶𝗰 𝗮𝗿𝗺 𝗳𝘂𝗹𝗹-𝗯𝗼𝗱𝘆 𝘁𝗼𝘂𝗰𝗵 𝘀𝗲𝗻𝘀𝗶𝘁𝗶𝘃𝗶𝘁𝘆 𝘄𝗶𝘁𝗵 𝗻𝗼 𝗮𝗿𝘁𝗶𝗳𝗶𝗰𝗶𝗮𝗹 𝘀𝗸𝗶𝗻 𝗻𝗲𝗲𝗱𝗲𝗱. They used internal force-torque sensors at 8 kHz + deep learning. The robot can feel where you touch it, recognize letters drawn on its surface, and respond to virtual buttons placed anywhere on its body. What's interesting is the infrastructure behind it. To train these models, you need high-frequency sensor streams, manifold learning to unfold trajectories, and the ability to iterate fast. They collected 2,300 samples from 20 people and hit 95.5% accuracy on digit recognition. This is what's possible when you have the right data infrastructure. 📄 lnkd.in/exgWfeXf Video credit: @DLR_en

Unitree G1 Kungfu Kid V6.0 A year and a half as a trainee — I'll keep working hard! Hope to earn more of your love🥰

Real time online 3D reconstruction of 3D scene and humans represented with SMPL. fanegg.github.io/Human3R/ I don't get tired of looking at these results

I think the real bitter lesson for robotics is going to be that *cheap robots deployed at scale* are going to let people solve the core robotics problems. And this is what we see from e.g. Unitree now, and increasingly companies like Galaxea.