Welcome to the CVPR 2025 conference!
Live Stream Information for Registered Attendees
Workshops and Tutorials Streaming
Some workshops and tutorials may choose to hold their event in Zoom. It is up to the organizer whether they stream. If available, the information to Join Zoom will appear on the workshop and tutorial page on the CVPR website. You must be registered with a virtual or physical registration and be logged in to see the Zoom information. It is also possible that some workshops will be recorded and posted on the website after the conference.
Not all tutorials that have a Zoom link visible will use their Zoom. Listed below are the workshops and tutorials that have a Zoom available to the audience. This does not guarantee they will hold their workshop in Zoom.
15 Tutorials
- Jun 11, 06:00 The 2nd Point Cloud Tutorial: All You Need To Know About 3D Point Cloud
- Jun 11, 06:00 Volumetric Video in the Real World
- Jun 11, 06:00 Scalable Generative Models in Computer Vision
- Jun 11, 06:00 From Video Generation to World Model
- Jun 11, 11:00 Evaluating Large Multi-modal Models: Challenges and Methods
- Jun 11, 11:00 Evaluations and Benchmarks in Context of Multimodal LLM
- Jun 12, 06:00 Multi-Modal Computer Vision and Foundation Models In Agriculture in conjunction with IEEE CVPR 2025
- Jun 12, 06:00 Animal re-identification
- Jun 12, 06:00 Computer Vision over Homomorphically Encrypted Data
- Jun 12, 06:00 Robotics 101: An Odyssey from A Vision Perspective
- Jun 12, 06:00 Continuous Data Cycle via Foundation Models
- Jun 12, 11:00 Recent Advances in Vision Foundation Models
- Jun 12, 11:00 Full-Stack, GPU-based Acceleration of Deep Learning and Foundation Models
- Jun 12, 11:00 Multimodal Mathematical Reasoning: Frontiers in Integrating Vision, Language, and Symbolic Representations
- Jun 12, 11:00 Power-efficient neural networks using low-precision data types and quantization
62 Workshops
- Jun 11, 06:00 The 2nd Workshop on Foundation Models for Medical Vision
- Jun 11, 06:00 10th New Trends in Image Restoration and Enhancement Workshop and Challenges
- Jun 11, 06:00 8th Workshop on Efficient Deep Learning for Computer Vision
- Jun 11, 06:00 M&M: Multi-modal Models and Medicine
- Jun 11, 06:00 Computer Vision for Mixed Reality
- Jun 11, 06:25 2nd MetaFood Workshop
- Jun 11, 06:30 8th Multimodal Learning and Applications Workshop
- Jun 11, 06:30 The 4th Workshop on Federated Learning for Computer Vision
- Jun 11, 06:30 The 1st Workshop on Humanoid Agents
- Jun 11, 06:45 3rd Workshop on Generative Models for Computer Vision
- Jun 11, 06:45 Workshop on Autonomous Driving
- Jun 11, 07:00 Mobile AI workshop and associated challenges, 5th edition
- Jun 11, 07:00 Workshop on Video Large Language Models
- Jun 11, 07:00 3D Vision Language Model for Robotics Manipulation: Opportunities and Challenges
- Jun 11, 07:00 Foundation Models Meet Embodied Agents
- Jun 11, 07:00 4th Workshop on Computer Vision in the Wild
- Jun 11, 07:00 Demographic diversity in computer vision
- Jun 11, 07:00 8th International Workshop on Visual Odometry and Computer Vision Applications Based on Location Clues
- Jun 11, 07:00 Uncertainty Quantification for Computer Vision
- Jun 11, 07:00 Embodied Intelligence for Autonomous Systems on the Horizon
- Jun 11, 07:50 Exploring the Next Generation of Data
- Jun 11, 10:45 Emergent Visual Abilities and Limits of Foundation Models (EVAL-FoMo 2)
- Jun 11, 11:00 AVA: Accessibility, Vision, and Autonomy Meet
- Jun 11, 11:00 The 4th Explainable AI for Computer Vision (XAI4CV) Workshop
- Jun 11, 11:00 2nd Workshop on Neural Fields Beyond Conventional Cameras
- Jun 11, 11:00 Image Matching: Local Features and Beyond
- Jun 11, 11:30 Multimodal Foundation Models for Biomedicine: Challenges and Opportunities
- Jun 11, 11:40 Multimodal Algorithmic Reasoning Workshop
- Jun 12, 06:00 Workshop on Visual Concepts
- Jun 12, 06:00 Workshop on Distillation of Foundation Models for Autonomous Driving
- Jun 12, 06:00 C3DV: 3rd Workshop on Compositional 3D Vision
- Jun 12, 06:00 WorldModelBench: The First Workshop on Benchmarking World Foundation Models
- Jun 12, 06:00 Workshop on Foundation and Large Vision Models in Remote Sensing
- Jun 12, 06:00 Workshop on 3D-LLM/VLA: Bridging Language, Vision and Action in 3D Environments
- Jun 12, 06:00 Workshop on Computer Vision for Microscopy Image Analysis
- Jun 12, 06:30 3D Digital Twin: Progress, Challenges, and Future Directions
- Jun 12, 06:30 SyntaGen: Harnessing Generative Models for Synthetic Visual Datasets
- Jun 12, 06:30 21th Workshop on Perception Beyond the Visible Spectrum (PBVS'2025)
- Jun 12, 06:30 VAND: Visual Anomaly and Novelty Detection - 3rd Edition
- Jun 12, 06:30 Women in Computer Vision
- Jun 12, 06:30 PixFoundation: Workshop on Pixel-level Vision Foundation Models
- Jun 12, 06:45 The 3rd Workshop on Sign Language Recognition, Translation and Production
- Jun 12, 06:45 Vision Meets Physics: Synergizing Physical Simulation and Computer Vision
- Jun 12, 06:50 2nd Workshop on Embodied "Humans": Symbiotic Intelligence between Virtual Humans and Humanoid Robots
- Jun 12, 06:55 Rhobin2025: The Third Rhobin Challenge on Reconstruction of Human-Object Interaction
- Jun 12, 07:00 Spatial Intelligence for Cultural Heritage
- Jun 12, 07:00 AI for Content Creation
- Jun 12, 07:00 Visual Generative Modeling: What’s After Diffusion?
- Jun 12, 07:00 Vision Language Models For All: Building Geo-Diverse and Culturally Aware Vision-Language Models
- Jun 12, 07:00 Test-time Scaling for Computer Vision
- Jun 12, 07:30 Computer Vision for Drug Discovery: Where are we and What is Beyond?
- Jun 12, 07:30 Agent in Interaction, from Humans to Robots
- Jun 12, 10:30 Visual Modeling Challenges for 2D-3D Virtual Try-On
- Jun 12, 10:30 Multi-modal Learning for Materials Science
- Jun 12, 11:00 11th IEEE International Workshop on Computer Vision in Sports
- Jun 12, 11:00 8th Workshop and Competition on Affective & Behavior Analysis in-the-wild
- Jun 12, 11:00 Domain Generalization: Evolution, Breakthroughs, and Future Horizons
- Jun 12, 11:00 The 6th International Workshop and Prize Challenge on Agriculture-Vision: Challenges & Opportunities for Computer Vision in Agriculture in conjunction with IEEE CVPR 2025
- Jun 12, 11:00 First Workshop on Experimental Model Auditing via Controllable Synthesis (EMACS)
- Jun 12, 11:20 The 4th Workshop on Transformers for Vision
- Jun 12, 11:30 Catch UAVs that Want to Watch You: Detection and Tracking of Unmanned Aerial Vehicle (UAV) in the Wild and the 4th Anti-UAV Workshop & Challenge
- Jun 12, 12:00 (4th) Monocular Depth Estimation Challenge
Papers with Pre-recorded Video Presentations
Posters and other events with recorded video are listed here.
Video Recordings
All video content from the conference will be posted here as it becomes available. Content from workshops is still in being processed.
Nashville Music City Center
Access location of exhibitors on the main floor.
Nashville Music City Wayfinding App (application is no longer available).
Slido
Use Slido for attendee engagement (Q&A, polls, etc) for plenary sessions: keynotes, planels, orals.
Getting Started
Everyone is expected to follow the Code of Conduct. We recommend to start by browsing the conference schedule. Read below to learn more about how to use virtual elements of the conference site. Thank you to all the organizers who made CVPR 2025 possible.
System Requirements
To access this site you will need a modern browser with JavaScript enabled. The website uses several external tools, namely Rocket.Chat, and Zoom. The login is handled through single sign-on through the virtual portal. You will not need to download any special software.
Navigating the Website
All virtual parts of CVPR 2025 will be accessed through this webpage and its menu bar at the top of the page. Check the Schedule to get an overview of when the live sessions for all events are taking place. You may navigate and visualize papers on the Papers page. If you go to your name in the top right corner and click on My Bookmarks in the dropdown menu, you can download the schedule with all sessions you bookmarked. You may also subscribe to your bookmarks using an iCal feed. The Schedule and Papers pages may be a bit slower to load the first time you access them.
Slido for Asking Plenary Event Questions
For plenary events, please use Slido to ask questions: https://app.sli.do/event/oqrd3oPv4p2phzDMuTGpYK/live/questions?m=oxuiy.
Rocket.Chat for Chatting with Authors of Papers
All attendees with registration will automatically have access to Rocket.Chat, a separate Rocket.Chat account is not needed. If you have problems with Rocket.Chat try refreshing the page or logging out and in again. When you run it enter the server URL: https://chat.thecvf.com. You may be prompted to log into CVPR.cc. After you log in, select Authenticate with OAuth and then click the blue Authorize button in the Authorize Rocket.Chat window. If you notice pop-up windows flickering, make the window taller.
Timezones
Your current timezone: . You can have the conference display the time in your timezone. Please check your timezone, and preferably choose a zone based on a city.
Calendar
You can build custom calendar of CVPR events you want to attend by clicking the events green flag or the green bookmark text next to the events date-time. To view your bookmarks click your name in the top right of the virtual site menu and select MyBookmarks. You can then subscribe to the calendar or download it and import it into your calendar.
Personal Program
CVPR partners with scholar-inbox.com to provide all attendees personalized conference programs based on personal research interests to more easily navigate the conference sessions. scholar-inbox.com is a community-driven paper recommender system developed by researchers for researchers. Registration at scholar-inbox.com is easy and fast. The personalized programs can be accessed from any mobile device or PC via web browser.
News & Careers
Keep up to date on the latest conference news by following CVPR 2025 on twitter and check out our News Gallery.
Job offers can be found at the CVPR 2025 Careers Website.
Code of Conduct
If you have concerns related to your inclusion at that conference, or observe someone else's difficulties, or have any other concerns related to inclusion, please use this Form report the issue. You can report a post in Rocket.Chat by hovering over the post, then click on the three vertical dots, and then select Report. This report is not anonymous.
Help
- For technical difficulties, please contact the Rocket.Chat #HelpDesk channel. You can get to it using the Help - Helpdesk RocketChat menu item.
- If you have problems with Rocket.Chat try refreshing the page and if that does not work try logging out and then logging back in.
- To report website issues use this Form.