Safety
Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware Fusion
arXiv:2609.03520v1 Announce Type: cross Abstract: In conditional coding-based neural video compression, the quality of temporal context directly affects compression per- formance. Existing methods mos
arXiv:2609.03520v1 Announce Type: cross Abstract: In conditional coding-based neural video compression, the quality of temporal context directly affects compression per- formance. Existing methods mostly construct context from prop- agated reference features, but they are vulnerable to motion esti- mation and local alignment errors in regions with complex mo- tion, occlusion, and high-frequency textures, resulting in inaccu- rate temporal information. To address this issue, this paper pro- poses a method combining deformable temporal alignment and difference-aware spatial selective fusion. A Context-aware Tem- poral Alignment Module is used to generate complementary tem- poral context, while a Difference-aware Spatial Selective Fusion module adaptively selects reliable temporal information and sup- presses misalignment. Experiments show that the proposed method achieves certain rate-distortion performance improve- ment over DCVC-DC.
Related
- StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation
- ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval
- Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective
Source: arXiv cs.AI | 2026-09-04