Lightnews — Scholar-powered news

Reposted by Stefano Esposito

Aaron Hertzmann @aaronhertzmann.com · 9d

Here's a recording of my talk on how perspective works! If you're interested in learning about how picture perspective works in human vision, this is the video to watch. #visionscience
www.youtube.com/watch?v=eamc...

Picture Perspective and Our Eyes

YouTube video by Aaron Hertzmann

www.youtube.com

2 6 19

Reposted by Stefano Esposito

Vision and Graphics Trends @si-cv-graphics.bsky.social · Sep 4

𝟯𝗗-𝗟𝗔𝗧𝗧𝗘: 𝗟𝗮𝘁𝗲𝗻𝘁 𝗦𝗽𝗮𝗰𝗲 𝟯𝗗 𝗘𝗱𝗶𝘁𝗶𝗻𝗴 𝗳𝗿𝗼𝗺 𝗧𝗲𝘅𝘁𝘂𝗮𝗹 𝗜𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻𝘀
Maria Parelli, Michael Oechsle, Michael Niemeyer ... Andreas Geiger
arxiv.org/abs/2509.00269
Trending on www.scholar-inbox.com

3 3

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · Sep 3

ellis.eu/news/ellis-p...

ELLIS PhD Program: Call for Applications 2025

The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...

ellis.eu

9 16

Reposted by Stefano Esposito

haoyuhe.bsky.social @haoyuhe.bsky.social · Aug 20

🚀 Introducing our new paper, MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models.

📄 Paper: www.scholar-inbox.com/papers/He202...
arxiv.org/pdf/2508.13148
💻 Code: github.com/autonomousvi...
🌐 Project Page: cli212.github.io/MDPO/

1 8 12

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · Jul 21

Today, we moved into our new building on the CyberValley campus. Everyone is super excited. PhD students went right back to work. But wait, is there something missing? ;)

1 1 35

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · Jul 18

Today we had our AVG Deep Cave Expedition Day! Exploring the challenges of the (unlit, narrow, crawling-only) Hofener Höhle near Grabenstetten ..

1 19

Reposted by Stefano Esposito

Zhenjun Zhao @ericzzj.bsky.social · Jul 17

SpatialTrackerV2: 3D Point Tracking Made Easy

Yuxi Xiao, @jianyuanwang.bsky.social, Nan Xue, @nikkar.bsky.social, Yuri Makarov, Bingyi Kang, Xing Zhu, Hujun Bao, Yujun Shen, Xiaowei Zhou

tl;dr: DAv2+VGGT->depths & poses->iterative cross-attention-based optimizer

arxiv.org/abs/2507.12462

2 2

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · Jul 15

In case you find it as relaxing as we do: Here is a 2h+ video of our autonomous RL driving agent CaRL in action! @danieldauner.bsky.social @bernhard-jaeger.bsky.social @kashyap7x.bsky.social
youtube.com/watch?v=_god...

CaRL: Learning Scalable Planning Policies with Simple Rewards

YouTube video by Daniel Dauner

youtube.com

5 21

Reposted by Stefano Esposito

Claire Vernade @claireve.bsky.social · Jul 15

At #ICML, you can just use scholar inbox to help you find your way through the poster sessions. It just sorts the papers according to your preferences and it really works.

www.scholar-inbox.com/conference/i... ICML 2025 Planner

3 5 50

Reposted by Stefano Esposito

Onno Eberhard @onnoeberhard.com · Jul 16

I am in Vancouver at ICML, and tomorrow I will present our newest paper "Partially Observable Reinforcement Learning with Memory Traces". We argue that eligibility traces are more effective than sliding windows as a memory mechanism for RL in POMDPs. 🧵

3 12 59

Reposted by Stefano Esposito

Bernhard Jaeger @bernhard-jaeger.bsky.social · Jul 15

We have released the code for our work, CaRL: Learning Scalable Planning Policies with Simple Rewards.

The repository contains the first public code base for training RL agents with the CARLA leaderboard 2.0 and nuPlan.

github.com/autonomousvi...

GitHub - autonomousvision/CaRL: [ArXiv 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards

[ArXiv 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards - autonomousvision/CaRL

github.com

7 20

Reposted by Stefano Esposito

Mehdi S. M. Sajjadi @msajjadi.com · Jul 10

Scaling 4D Representations

Self-supervised learning from video does scale! In our latest work, we scaled masked auto-encoding models to 22B params, boosting performance on pose estimation, tracking & more.

Paper: arxiv.org/abs/2412.15212
Code & models: github.com/google-deepmind/representations4d

8 20

Reposted by Stefano Esposito

Vision and Graphics Trends @si-cv-graphics.bsky.social · Jul 4

𝗚𝗲𝗼𝗺𝗲𝘁𝗿𝘆-𝗮𝘄𝗮𝗿𝗲 𝟰𝗗 𝗩𝗶𝗱𝗲𝗼 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗥𝗼𝗯𝗼𝘁 𝗠𝗮𝗻𝗶𝗽𝘂𝗹𝗮𝘁𝗶𝗼𝗻
Zeyi Liu, Shuang Li, Eric Cousineau ... Shuran Song
arxiv.org/abs/2507.01099
Trending on www.scholar-inbox.com

4 4

Reposted by Stefano Esposito

Zhenjun Zhao @ericzzj.bsky.social · Jul 4

MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details

Ruicheng Wang, Sicheng Xu, Yue Dong, Yu Deng, Jianfeng Xiang, Zelong Lv, Guangzhong Sun, Xin Tong, Jiaolong Yang

arxiv.org/abs/2507.02546

1 4 5

Reposted by Stefano Esposito

Andreas Geiger @andreasgeiger.bsky.social · Jul 3

I am very proud of my group! These are the nationalities of my current and past team members. Diversity is key.
🇩🇪 🇬🇷 🇮🇹 🇮🇳 🇷🇺 🇺🇦 🇨🇳 🇷🇸 🇯🇵 🇧🇪 🇺🇸 🇰🇷 🇹🇷

1 1 49

Reposted by Stefano Esposito

#CVPR2026 @cvprconference.bsky.social · Jun 15

That’s a wrap on #CVPR2025 in Nashville! From online convos to in-person vibes, one thing’s clear: this community is STRONG 💪 Thanks for following along!

Until next time. @deblinaml.bsky.social, @jbhaurum.bsky.social, @csprofkgd.bsky.social signing off.

3 12

Reposted by Stefano Esposito

Melanie Mitchell @melaniemitchell.bsky.social · Jun 14

LLM product placement and search optimization is here and it's as dystopian as you expected.

3 10 37

Stefano Esposito @s-esposito.bsky.social · Jun 15

Hey #CVPR2025! Curious about this work? I'll be presenting it this morning! Poster 31, from 10:30 to 12:30 🤠

@cvprconference.bsky.social

Stefano Esposito @s-esposito.bsky.social · May 5

📢 New paper CVPR 25!
Can meshes capture fuzzy geometry? Volumetric Surfaces uses adaptive textured shells to model hair, fur without the splatting / volume overhead. It’s fast, looks great, and runs in real time even on budget phones.
🔗 autonomousvision.github.io/volsurfs/
📄 arxiv.org/pdf/2409.02482

1 7

Reposted by Stefano Esposito

Angela Dai @adai.bsky.social · Jun 8

Check out the ScanNet++ workshop @CVPR on June 12 in 211 from 8:50am!

Exciting keynotes on state-of-the-art NVS & 3D understanding from Andrea Vedaldi, Cordelia Schmid, Gordon Wetzstein, Katja Schwarz, Qianqian Wang, and leading methods on the benchmark!

kaldir.vc.in.tum.de/scannetpp/cv...

6 14

Reposted by Stefano Esposito

Elliott / Shangzhe Wu @elliottwu.bsky.social · Jun 9

Join us for the 4D Vision Workshop #CVPR on June 11 starting at 9:20am!

We'll have an incredible lineup of speakers discussing the frontier of 3D computer vision techniques for dynamic world modeling across spatial AI, robotics, astrophysics, and more.

4dvisionworkshop.github.io

2 9

Reposted by Stefano Esposito

Ilya Chugunov @ilyac.info · Jun 9

This Wednesday (1-6PM, Room 106A) at CVPR @cvprconference.bsky.social we have a great lineup of keynote speakers, posters, and spotlights on neural fields and beyond: neural-bcc.github.io

Have a question you want answered by a panel of experts in the field? Send it to us via: tinyurl.com/bdddf36f

2 11

Reposted by Stefano Esposito

Haofei Xu @haofeixu.bsky.social · Jun 5

Excited to present our #CVPR2025 paper DepthSplat next week!
DepthSplat is a feed-forward model that achieves high-quality Gaussian reconstruction and view synthesis in just 0.6 seconds.
Looking forward to great conversations at the conference!

Andreas Geiger @andreasgeiger.bsky.social · Apr 24

🏠 Introducing DepthSplat: a framework that connects Gaussian splatting with single- and multi-view depth estimation. This enables robust depth modeling and high-quality view synthesis with state-of-the-art results on ScanNet, RealEstate10K, and DL3DV.
🔗 haofeixu.github.io/depthsplat/

3 7 27

Reposted by Stefano Esposito

Kashyap Chitta @kashyap7x.bsky.social · Jun 5

🚗 Pseudo-simulation combines the efficiency of open-loop and robustness of closed-loop evaluation. It uses real data + 3D Gaussian Splatting synthetic views to assess error recovery, achieving strong correlation with closed-loop simulations while requiring 6x less compute. arxiv.org/abs/2506.04218

10 22

Reposted by Stefano Esposito

Matthias Niessner @niessner.bsky.social · May 27

🚀🚀🚀Announcing our $13M funding round to build the next generation of AI: 𝐒𝐩𝐚𝐭𝐢𝐚𝐥 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 that can generate entire 3D environments anchored in space & time. 🚀🚀🚀

Interested? Join our world-class team:
🌍 spaitial.ai

youtu.be/FiGX82RUz8U

SpAItial AI: Building Spatial Foundation Models

YouTube video by SpAItial AI

youtu.be

4 9 53

Stefano Esposito @s-esposito.bsky.social · May 16

"ILM "artists" are now being paid to make shimpanzini bananini and bombardiro crocodilo"

Culture Crave 🍿 @culturecrave.co · May 16

Lucasfilm shares new concept #StarWars short film made with AI tools

(via TED)