SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix
This addresses the under-explored challenge of 3D stereoscopic video generation for applications in virtual reality and entertainment, though it is incremental as it builds on existing monocular video generation models.
The paper tackles the problem of generating 3D stereoscopic videos by proposing a pose-free and training-free method that warps monocular videos into stereoscopic views using estimated depth and a frame matrix inpainting framework, resulting in significant improvements over previous methods as validated on videos from models like Sora and Lumiere.
Video generation models have demonstrated great capabilities of producing impressive monocular videos, however, the generation of 3D stereoscopic video remains under-explored. We propose a pose-free and training-free approach for generating 3D stereoscopic videos using an off-the-shelf monocular video generation model. Our method warps a generated monocular video into camera views on stereoscopic baseline using estimated video depth, and employs a novel frame matrix video inpainting framework. The framework leverages the video generation model to inpaint frames observed from different timestamps and views. This effective approach generates consistent and semantically coherent stereoscopic videos without scene optimization or model fine-tuning. Moreover, we develop a disocclusion boundary re-injection scheme that further improves the quality of video inpainting by alleviating the negative effects propagated from disoccluded areas in the latent space. We validate the efficacy of our proposed method by conducting experiments on videos from various generative models, including Sora [4 ], Lumiere [2], WALT [8 ], and Zeroscope [ 42]. The experiments demonstrate that our method has a significant improvement over previous methods. The code will be released at \url{https://daipengwa.github.io/SVG_ProjectPage}.