Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Kaijin Chen, Dingkang Liang, Xin Zhou +4
Video world models have shown immense potential in simulating the physical world, yet existing memory mechanisms primarily treat environments as static canvases. When dynamic subje…
cs.CV2025
Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis
Yikang Ding, Jiwen Liu, Wenyuan Zhang +11
Recent advances in audio-driven avatar video generation have significantly enhanced audio-visual realism. However, existing methods treat instruction conditioning merely as low-lev…
cs.CV2024★ 3 cited
OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction
Jian Liu, Sipeng Zhang, Chuixin Kong +7
This technical report presents our solution, "occTransformer" for the 3D occupancy prediction track in the autonomous driving challenge at CVPR 2023. Our method builds upon the str…