Top Tweets for #EventCamera
We are excited to share that our #CORL2026 paper, "Approximate Imitation Learning for Event-based Quadrotor Flight in Cluttered Environments," where we learn end-to-end high-speed quadrotor flight from a single #EventCamera without the need to render events at training time!
Paper: https://t.co/zyX4Ksaohe
Video: https://t.co/5INlLCdNul
Event cameras are ideal for high-speed robotics thanks to their low latency and high temporal resolution. However, training event-based control policies is computationally expensive, as it requires rendering high-frame-rate video to simulate event streams. To overcome this bottleneck, we introduce "Approximate Imitation Learning," which decouples event-based representation learning from policy optimization. The key idea? Fine-tune the control policy without rendering a single event! This reduces training time by almost 30 times, from over 50 hours to 1.5 hours, without compromising performance. We demonstrate successful zero-shot, sim-to-real transfer, enabling agile flight through densely cluttered environments using a single event camera for visual perception. Although we apply our method only to event data, the framework is broadly applicable and can easily be extended to other modalities, which are computationally expensive to simulate, e.g., tactile sensors, radar, or LiDAR.
Kudos to Nico Messikommer, Jiaxu Xing, Leonard Bauersfeld, Marco Cannici, Elie Aljalbout!
@uzh_ifi @UZH_Science @UZH_en @UZHspacehub
@ERC_Research @UZH_ai @AUTOASSESS_EU @UZHspacehub
村上君(M1)・辻君(D2)の「Event-LiDAR」を #ECCV2026 で発表予定です!
LiDAR点群を3Dイベント化し、認識を効率化します。
📅 9/12 15:00 CEST
📍 ExHall・ポスター #12
#LiDAR #EventCamera #PointCloud #Robotics #AutonomousDriving #PhysicalAI
🚀 Can we make 3D perception more efficient by processing what changes across LiDAR scans?
We will present Event-LiDAR at #ECCV2026: converting conventional LiDAR scans into sparse 3D events.
Project: https://t.co/IMSozsF83O
Video: https://t.co/cWCbYTcFfs
Details below. 🧵
Event-LiDAR: 3D Eventification for Efficient Point Cloud Processing. #ECCV2026
Great work, Masatoshi Murakami & Eisho Tsuji!
📅 Sept 12 · 15:00 CEST
📍 ExHall · Poster #12
#LiDAR #EventCamera #PointCloud #Robotics #AutonomousDriving #PhysicalAI
🚀 Can we make 3D perception more efficient by processing what changes across LiDAR scans?
We will present Event-LiDAR at #ECCV2026: converting conventional LiDAR scans into sparse 3D events.
Project: https://t.co/IMSozsF83O
Video: https://t.co/cWCbYTcFfs
Details below. 🧵
1/ We are listening and actively improving. 🚀
Community feedback inspired a major update to EVIS, our Isaac Event Camera Plugin, and a new technical report.
📄 Arxiv: https://t.co/KuEW7U7p1h
💻 Code: https://t.co/jm2W9j27Tx
#EventCamera #ComputerVision #Robotics
Details:
Want to try event cameras for low-latency, high-speed robotics, but don’t have a physical sensor?
We’re open-sourcing an event camera plugin for NVIDIA Isaac Sim: plug-and-play, real-time, and highly configurable.
https://t.co/jm2W9j27Tx
#EventBasedVision #Robotics #IsaacSim
His thesis explores how event cameras can complement conventional frame-based cameras in challenging dark scenes, leading to new methods for efficient low-light video enhancement and event-RGB video reasoning.
#EventCamera #EventVision #ComputerVision #LowLightVision

This is a huge for the #EventCamera community! #BYD has just announced a new “flash-shot” camera for its next-generation intelligent driving stack, reportedly capable of up to 1000 fps with less than 1 ms latency
Why is this important?
For years, the event-camera and #NeuromorphicVision community has argued that autonomous systems should not be limited by conventional frame-based perception. In fast, safety-critical scenarios, milliseconds matter. Waiting tens of milliseconds for the next frame can be too slow when a pedestrian, cyclist, or vehicle suddenly appears. As recently shown in a Nature paper, the best is to combine both events and frames for low-latency and low-bandwidth automotive vision: https://t.co/iRNpgJr2jn
Whether BYD’s implementation is event-based, event-inspired, or a custom ultra-high-speed vision sensor, the message is clear: low-latency visual perception is moving from research labs into large-scale automotive deployment.
This is exactly the direction many of us have been advocating for more than a decade: cameras that do not just “see” the world, but react to visual changes with extremely low latency.
A major signal for the future of autonomous driving and a very exciting moment for everyone working on event cameras, neuromorphic vision, and high-speed robotic perception!
Btw we are hiring multiple PhD students and postdocs on event-based vision for automotive, autonomous vehicles, space, drones and more ;) Apply: https://t.co/T82J0Schvw
The video below is from BYD Intelligent Strategy Launch Conference, minute 1:12:00: https://t.co/MvJ7aGQFTH
@elonmusk
Joint work with Kai Kohyama, Yoshimitsu Aoki, Guillermo Gallego, Shintaro Shiba.
🌐 Project: https://t.co/GZ6yvzGLNs
📄 Paper: https://t.co/zMnFfhVrvW
💻 Code: https://t.co/IiTM7CNemy
#CVPR2026 #EventCamera #3DGS #NeuralRendering
#GTITrends What if cameras stopped capturing images and started detecting events? https://t.co/tyqccDllZc
#EventCamera #ComputerVision #NeuromorphicVision #AI #Robotics #GTISeminar @La_UPM @telecoupm

I'm happy to share this work finally enabling continuous robot control from a simulation pre-trained #eventcamera policy! Read our paper to learn how we overcome the large #sim2real event camera gap via depth prediction. We hope to enable agile, safer, vision-based robots!
🧵1/4
We are excited to share our #CORL2024 paper on learning quadrotor obstacle avoidance from the visual stream of a single #eventcamera! Trained entirely in simulation! We demonstrate obstacle avoidance both in the dark and in a forest up to 5m/s.
PDF: https://t.co/JLaQiolkXS
Video: https://t.co/kN73CASfH3
Project page: https://t.co/b52rvw8c5O
Event cameras are sensors that output per-pixel-level intensity changes at microsecond latency resolution; they feature nearly zero motion blur and high dynamic range but produce a very large volume of events under significant ego-motion and further lack a high-fidelity continuous-time sensor model in simulation, making direct #sim2real transfer not possible. By leveraging depth prediction as a pretext task, we pre-train a reactive obstacle avoidance policy with “approximated” simulated events and then fine-tune the perception component with limited events-and-depth real-world data. This technique bridges the sim2real gap for #eventcameras! As at the current state, there is no continuous-time sensor model for event cameras, we hope that this work can finally spur future research leveraging simulation for training event-vision-based policies to create faster, agile robots!
Kudos to @anishb1010, @marcocannic, @vijay_r_kumar @NikolaiMatni
@UZH_Science @UZH_en @UZHspacehub @uzh_ifi
@ERC_Research @GRASPlab @PennEngineers
We are excited to share our #CORL2024 paper on learning quadrotor obstacle avoidance from the visual stream of a single #eventcamera! Trained entirely in simulation! We demonstrate obstacle avoidance both in the dark and in a forest up to 5m/s.
PDF: https://t.co/JLaQiolkXS
Video: https://t.co/kN73CASfH3
Project page: https://t.co/b52rvw8c5O
Event cameras are sensors that output per-pixel-level intensity changes at microsecond latency resolution; they feature nearly zero motion blur and high dynamic range but produce a very large volume of events under significant ego-motion and further lack a high-fidelity continuous-time sensor model in simulation, making direct #sim2real transfer not possible. By leveraging depth prediction as a pretext task, we pre-train a reactive obstacle avoidance policy with “approximated” simulated events and then fine-tune the perception component with limited events-and-depth real-world data. This technique bridges the sim2real gap for #eventcameras! As at the current state, there is no continuous-time sensor model for event cameras, we hope that this work can finally spur future research leveraging simulation for training event-vision-based policies to create faster, agile robots!
Kudos to @anishb1010, @marcocannic, @vijay_r_kumar @NikolaiMatni
@UZH_Science @UZH_en @UZHspacehub @uzh_ifi
@ERC_Research @GRASPlab @PennEngineers
💥 [BREAKING] Prophesee introduces new SDK5 Pro!
Starting today, our 5x award-winning Metavision® SDK5 PRO software toolkit is now included with USB EVK purchases, at no additional cost.
#eventbased #eventbasedvision #EVS #eventcamera #metavision #sdk #neuromorphic
![Prophesee_ai's tweet photo. 💥 [BREAKING] Prophesee introduces new SDK5 Pro!
Starting today, our 5x award-winning Metavision® SDK5 PRO software toolkit is now included with USB EVK purchases, at no additional cost.
#eventbased #eventbasedvision #EVS #eventcamera #metavision #sdk #neuromorphic https://t.co/4Pckr4oICY](https://pbs.twimg.com/media/GZXEMhOW4AA8AjI.jpg)
🔗Read the article "Event Sensors Are Changing the Paradigm in Machine Vision" by our CEO Luca Verre and featured in @TechBriefsMag, to deep dive into how event-based vision is setting new standards in machine vision 👉https://t.co/W3kaTch4el
#eventcamera #eventbasedvision #iot

Thermal #ageing, neuro #prosthetic leg fully controlled by the brain, and cameras inspired by the small and quick movements of eyes that makes focusing on a moving object possible.
#LWnS with @PoortiKathpalia
#EventCamera #ProstheticLeg
#AMIEV #saccade
https://t.co/NQk78b1kYG
In humans, #microsaccades prevent fixated objects from fading in vision.
A rotating wedge prism does the same work for an #EventCamera that senses highly dynamic objects, according to a new study in Science #Robotics. https://t.co/qM1JPUqio3

And yes, for the group photo after my PhD thesis presentation, we recorded events with our @Prophesee_ai #eventcamera and reconstructed intensity images with our method HyperE2VID 🙂
(with @nazliikizler @aydinalatan @erkuterdem @eakbas2 and @haceryalimkeles)
👐 Our partner @Ultraleap is using our event-based Metavision® sensor GenX320 to enable ultra-smooth hands-free interaction via highly accurate gesture recognition and hand tracking capabilities.
Discover the power of GenX320 👉 https://t.co/7TWSkc6tBc
#evs #eventcamera

Never miss a moment with auto-share! Share-O-Matic makes it easy to instantly share all your precious wedding memories.
.
#eventcamera #photosharingapp #PhotoSharing #InstantShare #sharewithfriends #EventEssentials

How do we fund software for event cameras?
Event cameras are wonderful, but the tooling is abysmal! I am in touch with developers and manufacturers in the field to push open-source tools. There is plenty of talent, but how to fund this?
#neuromorphic #eventcamera #machinevision

Video recordings #CVPR2023 Workshop on Event-based Vision are now available: https://t.co/pCgbAZQPAK With @guillermogb @KostasPenn @CFermuller @DMigliorePro
#eventcamera @CVPRConf

Last Seen Hashtags on Sotwe
sex #caseros #colegialas
Seen from Argentina
校服捆绑
Seen from United States
incesto()*************************************************
Seen from Brazil
นัดสาวสวยกทม
Seen from Thailand
ometv safadinha
Seen from Brazil
turbanliifsa
Seen from Turkey
wldm
Seen from Poland
asian #bbc #bmaf #pornedit #jav
Seen from Malaysia
vibrator masturbating
Seen from South Africa
snaphack(*******)
Seen from Brazil
Trends for you
Most Popular Users

Elon Musk 
@elonmusk
240.5M followers

Barack Obama 
@barackobama
118.7M followers

Cristiano Ronaldo 
@cristiano
114.4M followers

Donald J. Trump 
@realdonaldtrump
111.8M followers

Narendra Modi 
@narendramodi
107M followers

Rihanna 
@rihanna
98.7M followers

NASA 
@nasa
92.2M followers

Justin Bieber 
@justinbieber
91.8M followers

KATY PERRY 
@katyperry
90M followers

Taylor Swift 
@taylorswift13
83.9M followers

Lady Gaga 
@ladygaga
75.5M followers

Virat Kohli 
@imvkohli
73.4M followers

Kim Kardashian 
@kimkardashian
70.8M followers

YouTube 
@youtube
68.7M followers

Neymar Jr 
@neymarjr
66.3M followers

Bill Gates 
@billgates
65.2M followers

Selena Gomez 
@selenagomez
63M followers

The Ellen Show
@theellenshow
62.1M followers

CNN 
@cnn
61.7M followers

X 
@x
60.6M followers
















