Oh yes, we started getting messages about towing truck at site since 4:11 pm. Finally it arrived at 7 pm.
We lost one day and had a lot of apprehensions.
The AVIS rental car broke down at 1 pm. Tow truck hasn’t arrived by 7 pm. TL;DR conversation with AVIS in the last 6 hours (continuous) : call cops to get out of the place. Assigned a replacement car 100 miles the opposite way. A friend had to drive 100 miles to get us #avis
Most insensitive comment!
When I calmly tried to explain that we are traveling with two senior citizens and a kid. We can’t arrive our destination even by midnight where we have a reserved hotel. Anthony answered “I can’t tell you where you spend your night. That’s your decision”
The hotel charged no show fee and we got to hear such insensitive comments.
A friend had from 100 miles to get us out of the place!
What’s the road side assistance fee is about?
@Avis provides uber voucher. But we needed a physical car to take us out of the place. Uber was unavailable! After 6-hours wait, who wants to hear “ma’am I can’t tell you where you spend the night. It’s your decision”
@Avis why do have customer care?
📢 Call for Papers! 1st Workshop on Computer Vision in Advertising and Marketing (CVAM)
📷ICCV 2025 @ICCVConference
📅 October 19-20, 2025
- Honolulu, Hawaii
Submit full-papers or extended abstract!
📷https://t.co/pyIsJOTACa
#ICCV2025#cfp
Introducing Open-TeleVision: https://t.co/eeYpxYX45m with Fully Autonomous policy video👇. We can conduct a long-horizon task with inserting 12 cans nonstop without any interruptions. We offer:
🤖 Highly precise and smooth bimanual manipulation.
📺 Active egocentric vision (with a moving neck) feedback.
It is achieved by imitation learning from teleoperation: We propose a VR-based REAL-TIME teleoperation that streams the stereo video observation from the robot camera to the VR device. The robot neck moves as the human head moves, the robot hands move as the human hands move, offering the operator an intuitive experience as the human herself becomes the robot.
The devils are all in the details, and how to implement things right:
✅How to perform IK/retargeting for smooth and precise control.
���How to do all these and also stream stereo video without no latency, all in real time.
We released our code here: https://t.co/HwOSbdFxrU
Active head hardware design:
https://t.co/Q3sQYppEhI
1/n
Intel and NYU present Image Sculpting
Precise Object Editing with 3D Geometry Control
paper page: https://t.co/aqDnDFBj4k
present Image Sculpting, a new framework for editing 2D images by incorporating tools from 3D geometry and graphics. This approach differs markedly from existing methods, which are confined to 2D spaces and typically rely on textual instructions, leading to ambiguity and limited control. Image Sculpting converts 2D objects into 3D, enabling direct interaction with their 3D geometry. Post-editing, these objects are re-rendered into 2D, merging into the original image to produce high-fidelity results through a coarse-to-fine enhancement process. The framework supports precise, quantifiable, and physically-plausible editing options such as pose editing, rotation, translation, 3D composition, carving, and serial addition. It marks an initial step towards combining the creative freedom of generative models with the precision of graphics pipelines.
A holiday present from #CVPR2024 to us, and from us to all #DL+#geometry folks: The 6th edition of #DLGC is accepted! New domains, new challenges, and new keynotes await!
Kudos to team @denabazazian, Géraldine Morin, Kathryn Leonard, @adarshk, @sellan_s, Aditya Balu, Sainan Liu.