CVPR 2026 receives record 16,092 paper submissions, a 24 percent increase over 2025, with about one-quarter accepted for presentation

CVPR 2026 drew 16,092 paper submissions, resulting in 4,089 accepted papers presented at the conference co-sponsored by the IEEE Computer Society and Computer Vision Foundation. The submission count represents a 24 percent increase over 2025.

The highest submission volumes came in image and video synthesis and generation; vision, language, and reasoning; multi-modal learning; 3-D from multiview and sensors; and medical and biological vision and cell microscopy. Accepted research includes advances in embodied and agentic intelligence (AI systems that perceive visual input and take actions), computational imaging, and visual security.

CVPR's acceptance rate has remained in the low-to-mid 20 percent range despite submissions more than doubling over the past five years. Past CVPR proceedings earned the number two spot in Google's 2025 Scholar Metrics, and Research.com ranks CVPR as the top conference for Computer Science, Image Processing & Computer Vision, and Machine Learning & Artificial Intelligence.