Plan-X: Instruct Video Generation via Semantic Planning
This addresses the challenge of generating videos that accurately follow complex user instructions for applications in visual synthesis, though it appears incremental as it builds on existing diffusion and language models.
The paper tackles the problem of visual hallucinations and mis-alignments in diffusion transformer-based video generation by proposing Plan-X, a framework that uses a Semantic Planner for high-level semantic planning, resulting in substantially reduced visual hallucinations and fine-grained, instruction-aligned video generation.
Diffusion Transformers have demonstrated remarkable capabilities in visual synthesis, yet they often struggle with high-level semantic reasoning and long-horizon planning. This limitation frequently leads to visual hallucinations and mis-alignments with user instructions, especially in scenarios involving complex scene understanding, human-object interactions, multi-stage actions, and in-context motion reasoning. To address these challenges, we propose Plan-X, a framework that explicitly enforces high-level semantic planning to instruct video generation process. At its core lies a Semantic Planner, a learnable multimodal language model that reasons over the user's intent from both text prompts and visual context, and autoregressively generates a sequence of text-grounded spatio-temporal semantic tokens. These semantic tokens, complementary to high-level text prompt guidance, serve as structured "semantic sketches" over time for the video diffusion model, which has its strength at synthesizing high-fidelity visual details. Plan-X effectively integrates the strength of language models in multimodal in-context reasoning and planning, together with the strength of diffusion models in photorealistic video synthesis. Extensive experiments demonstrate that our framework substantially reduces visual hallucinations and enables fine-grained, instruction-aligned video generation consistent with multimodal context.