We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry directly from disparity. To efficiently achieve consistent stereo generation, our approach introduces two key designs: (1) a unified camera-frame RoPE that augments latent tokens with camera-aware rotary positional encoding, enabling relative, view- and time-consistent conditioning while preserving pretrained video priors via a stable attention initialization; and (2) a stereo-aware attention decomposition that factors full 4D attention into 3D intra-view attention plus horizontal row attention, leveraging the epipolar prior to capture disparity-aligned correspondences with substantially lower compute. Across benchmarks, StereoWorld improves stereo consistency, disparity accuracy, and camera-motion fidelity over strong monocular-then-convert pipelines, achieving more than 3x faster generation with an additional 5% gain in viewpoint consistency. Beyond benchmarks, StereoWorld enables end-to-end binocular VR rendering without depth estimation or inpainting, enhances embodied policy learning through metric-scale depth grounding, and is compatible with long-video distillation for extended interactive stereo synthesis.
Figures & tables
Figure 2: World Model Comparison. StereoWorld incorporates metric-scale geometry, producing output modalities that are more compatible with pretrained models. Moreover, it can be applied end-to-end for VR visualization, ensuring better consistency of fine-grained details between the left and right views.
Figure 3: Illustration of StereoWorld. Given a pair of stereo images and a conditional camera trajectory, StereoWorld first encodes conditional and noisy video latents from different viewpoints and timesteps using a unified camera–frame RoPE representation. It then performs denoising through a DiT equipped with stereo attention, ultimately producing the final stereo video.
Figure 4: Stereo video generation comparison with SOTA methods augmented by post-hoc stereo conversion. Our method directly generates stereo video in an end-to-end manner, enabling better preservation of inter-view detail consistency and tonal coherence.
Figure 5: Visualization of camera trajectory comparison from methods with different camera conditioning types.
Figure 6: Stereo disparity comparison. Notably, our approach does not rely on any depth supervision during training.
Figure 7: Comparison of different camera-condition strategies.
Appendix figures & tables8 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 8: Attention mask configuration in distillation process.
Figure 9: More StereoWorld Results with Anaglyph.
Figure 10: The summary of quantitative feedback in the user study. (a) Camera Conformity (b) Temporal Consistency (c) Image Quality (d) Overall.
Figure 11: Stereo Video Generation on Embodided Scenarios.
Figure 12: Long Video Distillation Results.
Figure 13: Monocular and stereo generation comparison.
Figure 14: Effect of different baselines on StereoWorld.
Figure 15: Failure Case. Note that the blue road sign does not exist at the beginning of the sequence; however, as the viewpoint advances, it gradually emerges and increases in size.