arxiv:2610.29915

CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion

Published on Oct 21

· Submitted by

KaiZhu on Oct 27

Upvote

Authors:

Kai Zhu ,

Abstract

CausalAlign improves long-horizon camera ego-motion consistency in diffusion video generators by aligning internal representations to 3D dynamics via delta-token space.

Generated by thinkingmachines/Inkling-Small

Diffusion-based video generation models (VGMs) can produce visually plausible videos, yet their camera ego-motion often drifts over long horizons. Camera ego-motion determines how the viewpoint changes between frames and is essential for maintaining consistent geometry and trajectories. To address this problem, we propose CausalAlign, a causal alignment framework with two components. First, we diagnose how precise ego motion is represented, used, and retained within VGMs using linear probes and causal interventions, revealing a rise-and-fall pattern during denoising. Second, we strengthen ego-motion state in VGM by aligning the representations at the identified layers to a 3D foundation model through delta-token space. This space encodes the changes between consecutive frames, allowing the alignment to focus on ego-motion dynamics rather than static scene content. With Wan2.2 fine-tuned on DL3DV and RealEstate10K, CausalAlign can largely improve motion accuracy, geometric consistency, and temporal smoothness, while preserving visual quality. For example, it improves geometric consistency by more than 20% relative to the base model. Moreover, with the fine-tuned VGM, CausalAlign improves the success rate of world action models (WAMs) by 10 points on mobile manipulation tasks of RoboCasa365 benchmark. Overall, CausalAlign improves ego-motion consistency in diffusion-based VGMs and yields noticeable gains in embodied models.

View arXiv page View PDF Project page GitHub 7 Add to collection

Community

j-zhu

Paper author Paper submitter about 23 hours ago

Diffusion-based video generation models (VGMs) can synthesize visually compelling content, but maintaining geometrically consistent camera ego-motion across frames remains an open problem. Camera ego-motion describes these cross-frame viewpoint changes; geometrically inconsistent future predictions can induce systematic errors in downstream action prediction. To address this problem, we propose CausalAlign, a framework combining causal diagnosis and delta-token alignment.

First, we diagnose how ego-motion is represented, used, and retained within VGMs using linear probes and causal interventions. In the base model, both measures rise and then fall across denoising layers and timesteps: ego-motion is used at intermediate stages but is not retained later, a pattern we call geometric state forgetting. Second, we construct a delta-token space from a 3D foundation model and align VGM representations where ego-motion begins to fade. Delta tokens encode changes between consecutive frames, focusing supervision on motion rather than redundant static scene content.

With Wan2.2 fine-tuned on DL3DV and RealEstate10K, CausalAlign preserves visual quality while improving motion accuracy, geometric consistency, and temporal smoothness. For example, it reduces geometric consistency errors by more than 20% relative to the base model. Moreover, using the fine-tuned VGM, CausalAlign improves downstream world action models (WAMs) on the RoboCasa365 benchmark. Overall, CausalAlign improves ego-motion consistency in diffusion-based VGMs and yields gains in downstream embodied models on motion-intensive tasks.