Newest papers

WorldForge V2: Eliciting Camera-Trajectory Alignment in Video Diffusion Models

Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li, Joey Tianyi Zhou, Chi Zhang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31640 · cited by 0 works (OpenAlex) · open-access PDF

German

Diese korrigierten Einzelkamera-Difusion-Modelle haben reiche 3D/4D-Daten-Priors erlernt, was sie für die Szenengeneration und das Video-Rendering vielversprechend macht. Allerdings ist ihre Verwendung in räumlichen Aufgaben durch unpräzise Kamerakontrolle, räumliche und zeitliche Inkonsistenzen und verflochtende Kamerabewegung mit Szenendynamik begrenzt. Bestehende Ansätze, wie z. B. Aufgabenspezifisches Fein-Tuning und Post-Prozess-Warping, führen oft visuelle Artefakte ein, verallgemeinern schlecht oder erleiden hohe berechnende Kosten. Wir schlagen WorldForge V2 vor, um präzise Kamerakontrolle zu erreichen und gleichzeitig die generativen Fähigkeiten von vorbereiteten Video-

Machine translation (Meta M2M100); the English original follows.

Abstract

Video diffusion models have learned rich 3D/4D priors, making them promising for scene generation and video re-rendering. However, their use in spatial tasks is limited by imprecise camera control, spatial and temporal inconsistencies, and entangled camera motion with scene dynamics. Existing approaches, such as task-specific fine-tuning and post-process warping, often introduce visual artifacts, generalize poorly, or incur high computational costs. We propose WorldForge V2 to achieve accurate camera control while preserving the generative capabilities of pretrained video models. We first develop a training-free guidance framework using warped references to iteratively refine generation along a target camera path. Optical-flow analysis identifies motion-related latent channels for selective guidance, helping separate motion control from appearance. A dual-path strategy further compares guided and unguided predictions to correct artifacts from imperfect references. Together, these components guide viewpoint changes while preserving scene appearance and object motion. To reduce refinement costs, v-cache approximates the correction using the preceding denoising prediction, avoiding an additional model evaluation. We further extend motion localization from latent channels to network blocks and introduce Trajectory LoRA, which concentrates adaptation on blocks most responsive to trajectory guidance. A two-stage training strategy teaches these adapters to denoise the states encountered during guided generation, using limited supervision effectively. This enables reliable camera control with very little training data, with a single training scene already supporting generalization to unseen scenes. Quantitative and qualitative evaluations across multiple datasets show that our method achieves state-of-the-art generation quality and trajectory accuracy in camera-controlled video generation.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Artificial intelligence, Computer vision, Trajectory, Motion (physics), Generalization

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange