[R] CVPR'26 SPAR-3D Workshop Call For Papers

2026-03-01 · Source: Machine Learning · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy · Depth: Expert, quick

Summary

The SPAR-3D workshop at CVPR 2026 has extended its submission deadline to March 21, 2026. This workshop focuses on security, privacy, adversarial robustness, and reliability within 3D vision models. It welcomes research specifically addressing these areas, as well as broader 3D vision papers that include a substantial discussion on robustness, safety, or trustworthiness. Submissions can integrate these topics as a dedicated section or paragraph within a larger technical contribution. The workshop aims to gather diverse research exploring critical aspects of trustworthy 3D vision.

Key takeaway

For AI Scientists and Research Scientists developing 3D vision models, consider submitting your work to the SPAR-3D workshop at CVPR 2026. The extended deadline of March 21, 2026, provides additional time to prepare submissions focusing on security, privacy, adversarial robustness, or reliability. Even if your primary contribution is broader, ensure your paper includes a dedicated section on trustworthiness or safety to align with the workshop's scope.

Key insights

The SPAR-3D workshop at CVPR 2026 seeks papers on security, privacy, robustness, and reliability in 3D vision.

Principles

• Robustness is critical for 3D vision.
• Safety and trustworthiness are key considerations.

In practice

• Submit 3D vision work to SPAR-3D.
• Include robustness discussions in papers.

Topics

• 3D Vision
• Adversarial Robustness
• AI Security
• AI Privacy
• Model Reliability

Best for: AI Scientist, Research Scientist, AI Researcher, AI Engineer, Computer Vision Engineer

Related on AIssential

• PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models — The article introduces a large-scale, pre-generated dataset, PHANTOM, to democratize VLM adversarial attack research and improve safety evaluations.
• v318: Proceedings of Canadian Conference on AI — AI research is rapidly advancing across efficiency, robustness, and diverse real-world applications.
• CVPR 2026 Papers with Code & Data — Publicly available code and data accelerate computer vision research and community engagement.
• Hybrid Robustness Verification for Spatio-Temporal Neural Networks — STBP offers a scalable, precise method for verifying 3D CNN robustness by modeling realistic spatio-temporal adversarial constraints.
• SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection — Jointly sparsifying 2D image tokens and 3D object queries with relevance-aligned filtering significantly boosts multi-view 3D detection efficiency.
• NavTrust: Benchmarking Trustworthiness for Embodied Navigation — NavTrust benchmarks embodied navigation trustworthiness by systematically corrupting inputs to reveal robustness gaps.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine Learning.