CVPR 2027 Call for Papers

Papers in the main technical program must describe high-quality, original research. Topics of interest cover all aspects of computer vision and pattern recognition including, but not limited to:

3D reconstruction and geometry: single-view, multi-view, depth, and sensors
Trustworthy, responsible and explainable vision
Generative AI Safety and Authenticity
Deep learning architectures and techniques
Computational imaging and cameras
Vision applications, systems and social impact
Theory, optimization, and statistical learning for vision
Low-level vision
Physics-based vision and shape-from-X
Document analysis and understanding
Human-centric vision and biometrics
Data synthesis, datasets and benchmarks
Efficient and scalable vision
Multimodal learning
Image and video synthesis and generation
Mulitmodal Generative and Foundation Models
Reasoning & Reinforcement Learning

Recognition: Categorization, detection, retrieval
Segmentation, grouping and shape analysis
Representation learning
Embodied vision and robotics
Agentic AI
Physical AI: World Models, VLA, Planning, Simulation
Autonomous driving
Scene analysis and understanding
Self-, semi-, meta- and unsupervised learning
Transfer / low-shot / continual / long-tail learning
Photogrammetry, remote sensing and multi-sensors
Video understanding, motion and tracking
Vision + graphics
AI for Science and Scientific Discovery
AI for Education
Medical and biological vision, cell microscopy

Important Dates

Paper Registration Deadline*:
Submission Deadline*:
Supplementary Materials Deadline:
Reviews Released:
Rebuttal Period:
Final Decisions:

Nov 10, 2026 AOE
Nov 16, 2026 AOE
Nov 23, 2026 AOE
Jan 25, 2027 AOE
January 25 - February 1, 2027 AOE
Feb 25, 2027 AOE

* Date is fixed, no extension will be given

AOE = Anywhere On Earth

Paper Submission

All submissions will be handled electronically via the OpenReview conference submission website https://openreview.net/group?id=thecvf.com/CVPR/2027/Conference. All authors must agree to the policies stipulated below. The submission deadline is November 16th, 2026 Anywhere on Earth (UTC-12) and will not be changed. Supplementary materials can be submitted until November 23rd, 2026 Anywhere on Earth (UTC-12).

An up-to-date OpenReview profile for all co-authors is required to submit a paper. Note that new profiles created without an institutional email will go through a moderation process which can take up to two weeks. New profiles created with an institutional email will be activated automatically.

Submission Requirements and Policies

Dual Submission Policy. By submitting to CVPR, authors confirm that no substantially similar paper has been or will be submitted to another conference or workshop during the review period (November 16, 2026 – February 22, 2027). For complete dual submission guidelines and prior work policies, see the Author Guidelines on the conference website.

Review Process Agreement. By submitting a paper, authors agree to participate in the review process and understand that OpenReview will automatically match manuscripts to appropriate reviewers and area chairs based on expertise.

Mandatory Reviewer Service. All authors commit to serve as reviewers, area chairs, or senior area chairs when invited by the program chairs. Exceptions are granted only for truly exceptional circumstances that must be:

Disclosed to the program chairs in advance
Approved by the program chairs as valid reasons for exemption

This policy follows PAMI Technical Committee guidelines and recent conference practices.

IEEE submission policies: https://conferences.ieeeauthorcenter.ieee.org/author-ethics/guidelines-and-policies/submission-policies/

Publication and Patent Disclosure

All accepted papers will be publicly released by the Computer Vision Foundation (CVF) two weeks before the conference. Authors considering patent applications should note that the paper's official public disclosure date is whichever occurs first:

Two weeks before the conference, or
When authors make the paper publicly available themselves

More information about CVF: https://www.thecvf.com

LLM Usage

CVPR 2027 will make use of large language models (LLMs) in selected parts of the conference and reviewing process. The exact scope, permitted uses, and associated guidelines are currently being finalized. This section will be updated with further details before the submission deadline.

Contemporaneous Work

For the purpose of the reviewing process, papers that appeared online after September 15th, 2026 will generally be considered "contemporaneous" in the sense that the submission will not be rejected on the basis of the comparison to contemporaneous work. Authors are still expected to cite and discuss contemporaneous work and perform empirical comparisons to the degree feasible. Any paper that influenced the submission is considered prior work and must be cited and discussed as such. Submissions that are very similar to contemporaneous work will undergo additional scrutiny to prevent cases of plagiarism and missing credit to prior work. We do not distinguish arxiv papers and other published (conference & journal) papers, and the Contemporaneous-Work rule applies in the same way. More nuanced judgements, including how to determine the date of publication, will be made by the area chair handling the submission.