5 papers
Anti-Aliasing Snapshot HDR Imaging Using Non-Regular Sensing
Teresa Stürzenhofäcker, Moritz Klimm, Jürgen Seiler +1
Snapshot HDR imaging is essential to capture the full dynamic range of a scene in a single exposure, making it essential for video and dynamic environments where motion prevents th…
Optimized Learned Image Compression for Facial Expression Recognition
Xiumei Li, Marc Windsheimer, Misha Sadeghi +2
Efficient data compression is crucial for the storage and transmission of visual data. However, in facial expression recognition (FER) tasks, lossy compression often leads to featu…
Lossless 4:2:0 Screen Content Coding Using Luma-Guided Soft Context Formation
Hannah Och, André Kaup
The soft context formation coder is a pixel-wise state-of-the-art lossless screen content coder using pattern matching and color palette coding in combination with arithmetic codin…
Improved Motion Plane Adaptive 360-Degree Video Compression Using Affine Motion Models
Marina Ritthaler, Andy Regensky, André Kaup
Efficient compression of 360-degree video content requires the application of advanced motion models for interframe prediction. The Motion Plane Adaptive (MPA) motion model project…
OSLO-IC: On-the-Sphere Learned Omnidirectional Image Compression with Attention Modules and Spatial Context
Paul Wawerek-López, Navid Mahmoudian Bidgoli, Pascal Frossard +2
Developing effective 360-degree (spherical) image compression techniques is crucial for technologies like virtual reality and automated driving. This paper advances the state-of-th…