Content Adaptive based Motion Alignment Framework for Learned Video Compression
By: Tiange Zhang, Xiandong Meng, Siwei Ma
Potential Business Impact:
Makes videos smaller without losing quality.
Recent advances in end-to-end video compression have shown promising results owing to their unified end-to-end learning optimization. However, such generalized frameworks often lack content-specific adaptation, leading to suboptimal compression performance. To address this, this paper proposes a content adaptive based motion alignment framework that improves performance by adapting encoding strategies to diverse content characteristics. Specifically, we first introduce a two-stage flow-guided deformable warping mechanism that refines motion compensation with coarse-to-fine offset prediction and mask modulation, enabling precise feature alignment. Second, we propose a multi-reference quality aware strategy that adjusts distortion weights based on reference quality, and applies it to hierarchical training to reduce error propagation. Third, we integrate a training-free module that downsamples frames by motion magnitude and resolution to obtain smooth motion estimation. Experimental results on standard test datasets demonstrate that our framework CAMA achieves significant improvements over state-of-the-art Neural Video Compression models, achieving a 24.95% BD-rate (PSNR) savings over our baseline model DCVC-TCM, while also outperforming reproduced DCVC-DC and traditional codec HM-16.25.
Similar Papers
Motion-Aware Concept Alignment for Consistent Video Editing
CV and Pattern Recognition
Changes video objects to match a picture.
Track and Caption Any Motion: Query-Free Motion Discovery and Description in Videos
CV and Pattern Recognition
Lets computers describe what's happening in videos.
Error-Propagation-Free Learned Video Compression With Dual-Domain Progressive Temporal Alignment
CV and Pattern Recognition
Makes videos stream smoothly without errors.