UBC Computer Science debuts 5 papers at leading computer vision and pattern recognition conference
From a model to observe Earth to a new approach for scene reconstruction, UBC Computer Science researchers present new research at the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026
Header image from Ajisafe et al. (2026).
UBC Computer Science researchers will be presenting new research at the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) from June 3-7, 2026 in Colorado, USA. CVPR is the premier computer vision conference for researchers to share the latest findings in areas such as AI, autonomous vehicles and robotics.
Researchers from UBC will debut five papers at the main conference and one paper at the conference workshops.
In addition to papers, UBC Computer Science PhD students Aditya Chinchure and Sahithya Ravi, Assistant Professor Vered Shwartz and Professor Leonid Sigal are part of the organizing committee for the CogVL: Cognitive Foundations for Multimodal Models workshop. Assistant Professor Peter Yichen Chen is part of the organizing committee for the 3D Geometry Generation for Scientific Computing workshop while Assistant Professor Evan Shelhamer is a panelist at the Bitter Lessons in Computer Vision workshop. Several of our faculty served as Area Chairs to help curate the technical program for the conference: Assistant Professors Evan Shelhamer and Kwang Moo Yi and Professor Leonid Sigal.
The following papers will be presented at the conference:
InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Models
Shunsuke Sakai, Xiangteng He, Chunzhi Gu, Leonid Sigal, Tatsuhito Hasegawa
Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection
Qian Yang, Shivam Chandhok, Oscar Mañas, Kanishk Jain, Aishwarya Agrawal, Leonid Sigal
OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
Henry Herzog, Favyen Bastani, Yawen Zhang, Gabriel Tseng, Joseph Redmon, Hadrien Sablon, Ryan Park, Jacob Morrison, Alexandra Buraczynski, Karen Farley, Josh Hansen, Andrew Howe, Patrick Alan Johnson, Mark Otterlee, Ted Schmitt, Hunter Pitelka, Stephen Daspit, Rachel Ratner, Christopher Wilhelm, Sebastian Wood, Mike Jacobi, Hannah Kerner, Evan Shelhamer, Ali Farhadi, Ranjay Krishna, Patrick Beukema
PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
Yuanhang Lei, Tao Cheng, Xingxuan Li, Boming Zhao, Siyuan Huang, Ruizhen Hu, Peter Yichen Chen, Hujun Bao, Zhaopeng Cui
Semantic Foam: Unifying Spatial and Semantic Scene Decomposition
Amr Sharafeldin, Aryan Mikaeili, Thomas Walker, Shrisudhan Govindarajan, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
The following paper will be presented at CVPR workshops: