arXiv Computer Vision
FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 16
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
arXiv:2609.17521v1 Announce Type: cross Abstract: Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet...
Hugging Face Trending Papers
Sep 15
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control
Interactive control for video generation is moving from coarse prompts toward fine-grained, physically meaningful manipulation of dynamic scenes. Yet existing controllable methods either require the f...
arXiv AI
Aug 21
Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
arXiv:2608. 19556v1 Announce Type: cross Abstract: Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion.
Hugging Face Trending Papers
Jul 14
FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
World Action Models (WAMs) are able to leverage pretrained video generators for both world modeling and action prediction. However, directly leveraging such video generators for control raises a new challenge: how to represent actions in a suitable form that aligns with pretrained video generators while carrying enough motion cues for accurate control.
Hugging Face Trending Papers
Aug 20
Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion. Recent bidirectional approaches address this problem using rewards signals built upon 3D Gaussian-Splatting reconstruction.
arXiv AI
1d ago
Triangular Resampling for Long-Horizon Motion Generation
arXiv:2609.34697v2 Announce Type: replace-cross Abstract: We introduce Triangular Resampling (TR), a post-training method for mitigating long-horizon error accumulation in motion diffusion models. Bu...