IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

Apple sponsored the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), which took place in person from June 18 to 22 in Vancouver, Canada. CVPR is the annual computer vision event comprising the main conference and several co-located workshops and short courses. Below was the schedule of our sponsored workshops and events at CVPR 2023.

Accepted Papers

AutoFocusFormer: Image Segmentation off the Grid

Chen Ziwen, Kaushik Patnaik, Shuangfei Zhai, Alvin Wan, Zhile Ren, Alex Schwing, Alex Colburn, Li Fuxin

DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection

Xuan Zhang, Shiyu Li, Xi Li, Ping Huang, Jiulong Shan, Ting Chen

FaceLit: Neural 3D Relightable Faces

Anurag Ranjan, Kwang Moo Yi, Jen-Hao Rick Chang, Oncel Tuzel

MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices

Kejie Li, Jia-Wang Bian, Robert Castle, Philip H.S. Torr, Victor Adrian Prisacariu

MobileOne: An Improved One millisecond Mobile Backbone

Pavan Kumar Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel and Anurag Ranjan

PointConvFormer: Revenge of the Point-based Convolution

Wenxuan Wu, Li Fuxin, Qi Shan

Pointersect: Neural Rendering with Cloud-Ray Intersection

Jen-Hao Rick Chang, Wei-Yu Chen, Anurag Ranjan, Kwang Moo Yi, Oncel Tuzel

Self Supervision Does Not Help Natural Language Supervision at Scale

Floris Weers, Vaishaal Shankar, Angelos Katharopoulos, Yinfei Yang, Tom Gunter

Demos

RoomPlan

RoomPlan technology enables the user to efficiently capture a room and its defining objects in a parametric format, completing the process within minutes. The capture progress is automatically displayed in an intuitive and user-friendly manner. The final room capture is delivered as a parametric representation and can optionally be exported to USD, USDA or USDZ formats. The technology is supported on any of the Apple devices (iPads and iPhones) equipped with LiDAR sensors and will enable applications across different fields, including interior design, architecture, real estate and E-commerce.

Building on its robust foundation, RoomPlan now offers enhanced access to underlying ARKit technologies, further expanding its capabilities. This includes support for multiple rooms, object attributes, intricate wall and floor shapes, and room categorization. These enhancements allow users to fully harness the potential of RoomPlan, creating an even more versatile and comprehensive solution for a wide range of applications.

Object Capture

Object Capture allows users to generate high‑quality 3D models from a series of photos taken on their iPhone or iPad. Using CVML algorithms, Object Capture is able to analyze the overlap area between different images to match up landmarks, and then produce a 3D model of a photographed object. These models can then be viewed in AR Quick Look, seamlessly integrated into your Xcode project, or used in professional 3D content workflows.

All CVPR attendees were invited to stop by the Apple booth to experience these demos in person.

Acknowledgements

Vladlen Koltun is a program chair for CVPR 2023.

David Hafner is a technical chair for CVPR 2023.

Alexander Toshev is an area chair for CVPR 2023.

Chen Huang, Chia-Yin Tsai, Jason Ramapuram, Kevin Chen, Pau Rodriguez Lopez, Vaishaal Shankar, and Zhile Ren are reviewers for CVPR 2023.

Haoping Bai, Meng Cao, Oncel Tuzel, and Tatiana Likhomanenko are organizers for the Vision-based InduStrial InspectiON workshop.

Arsalan Farooq, Carrie Yu, Haoping Bai, Meng Cao, Oncel Tuzel, Parham Shahidi, Shuangfei Zhai, Tatiana Likhomanenko, and Weston Li are challenge organizers for the Vision-based InduStrial InspectiON workshop

Ali Farhadi, Jiulong Shan, Rahul Kapoor, and Samy Bengio are members of the Vision-based InduStrial InspectiON workshop advisory committee.

Tatiana Likhomanenko and Vimal Thilak are reviewers for the Vision-based InduStrial InspectiON workshop

Devon Hjelm and Rin Metcalf are organizers for the Embodied AI workshop

Alexander Toshev and Ali Farhadi are members of the Embodied AI workshop scientific advisory board.

Jeffrey Bigham is an organizer for the VizWiz Grand Challenge workshop.

Pau Rodriguez Lopez is an area chair for the Continual Learning in Computer Vision workshop.

Pau Rodriguez Lopez is a general chair for the Learning with Limited Labelled Data for Image and Video Understanding workshop.