arXiv Computer Vision
Memory-Guided B-Roll Generation from User Video Collections
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
4d ago
Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation
arXiv:2609.37407v1 Announce Type: new Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a ma...
arXiv Computer Vision
Sep 24
The Past Frames the Future: Memory for Autoregressive Video Generation
arXiv:2609.28466v1 Announce Type: new Abstract: Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environme...
arXiv AI
Jul 16
GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling
arXiv:2606. 20799v2 Announce Type: replace-cross Abstract: Generating visually consistent multi-shot videos remains an open challenge.
arXiv AI
Aug 19
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation
SemComp-Bench introduces a new video generation task called Semantic Task Completion, where a model must produce a video that achieves a specified outcome while maintaining semantic alignment with a reference image. The benchmark includes the SemComp-Data dataset, spanning six domains, and a four-stage curation pipeline that transforms raw videos into standardized instances. Evaluation is performed via a vision‑language model that answers structured binary questions, yielding Outcome Achievement (OA) and Generation Reliability (GR) scores.
arXiv Computer Vision
2d ago
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
OneStreamer is a streaming video model that jointly learns to record evidence and respond to tasks through a shared proactive generation process. Its Proactive Hierarchical Caption Memory creates time‑grounded local‑detail captions and event summaries, while Proactive State Transition Learning reduces waiting states by supervising all output anchors. The authors also built a large OneStreamer‑1M dataset and show that a 4B model outperforms baselines on eight streaming video benchmarks, with ablations confirming the benefits of generated captions and PSTL.
arXiv AI
Jun 15
CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation
arXiv:2606. 13768v1 Announce Type: cross Abstract: Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions.