5 papers
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Haocheng Xi, Yiming Xie, Hexu Zhao +8
Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck. Linear attention offers an appeal…
Streaming Video Generation with Streaming Force Control
Hanhui Wang, Yiming Xie, Haiwen Feng +3
We introduce StreamForce, a streaming video generation framework that enables physically grounded control through continuous force inputs. Unlike prior video models that train sepa…
Self-Improving 4D Perception via Self-Distillation
Nan Huang, Pengcheng Yu, Weijia Zeng +4
Large-scale multi-view reconstruction models have made remarkable progress, but most existing approaches still rely on fully supervised training with ground-truth 3D/4D annotations…
Toward Human Understanding with Controllable Synthesis
Hanz Cuevas-Velasquez, Priyanka Patel, Haiwen Feng +1
Training methods to perform robust 3D human pose and shape (HPS) estimation requires diverse training images with accurate ground truth. While BEDLAM demonstrates the potential of…
SynthForge: Synthesizing High-Quality Face Dataset with Controllable 3D Generative Models
Abhay Rawat, Shubham Dokania, Astitva Srivastava +3
Recent advancements in generative models have unlocked the capabilities to render photo-realistic data in a controllable fashion. Trained on the real data, these generative models…