Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding

• URL: http://arxiv.org/abs/2512.14236v1
• Date: Tue, 16 Dec 2025 09:46:23 GMT
• Title: Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding
• Abstract summary: Elastic3D is a controllable, direct end-to-end method for upgrading a conventional video to a binocular one.<n>Key to its high-quality stereo video output is a novel, guided VAE decoder.
• Score: 62.69753250254731
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The growing demand for immersive 3D content calls for automated monocular-to-stereo video conversion. We present Elastic3D, a controllable, direct end-to-end method for upgrading a conventional video to a binocular one. Our approach, based on (conditional) latent diffusion, avoids artifacts due to explicit depth estimation and warping. The key to its high-quality stereo video output is a novel, guided VAE decoder that ensures sharp and epipolar-consistent stereo video output. Moreover, our method gives the user control over the strength of the stereo effect (more precisely, the disparity range) at inference time, via an intuitive, scalar tuning knob. Experiments on three different datasets of real-world stereo videos show that our method outperforms both traditional warping-based and recent warping-free baselines and sets a new standard for reliable, controllable stereo video conversion. Please check the project page for the video samples https://elastic3d.github.io.

Related papers

• Geometric Reciprocity: Unlocking Self-Supervision for Stereoscopic Video Generation [17.05562746375872]
  Training-based methods achieve superior quality but rely on scarce stereo pairs or synthetic data with domain gaps.<n>We address this through the first self-supervised framework learning from monocular videos via cycle consistency.<n>This yields train-test consistency for the stated warping formulation, supporting self-supervised learning from unlimited monocular videos.
  arXiv  Detail & Related papers  (2026-07-06T17:32:04Z)
• Stereo World Model: Camera-Guided Stereo Video Generation [52.3922115596956]
  We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.<n>Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry directly from disparity.
  arXiv  Detail & Related papers  (2026-03-18T05:42:22Z)
• StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors [41.34827274890319]
  We introduce UniStereo, the first large-scale unified dataset for stereo video conversion.<n>We propose StereoPilot, an efficient feed-forward model that directly synthesizes the target view without relying on explicit depth maps.<n>Experiments demonstrate that StereoPilot significantly outperforms state-of-the-art methods in both visual fidelity and computational efficiency.
  arXiv  Detail & Related papers  (2025-12-18T18:59:50Z)
• StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation [108.97993219426509]
  StereoWorld is an end-to-end framework for high-fidelity monocular-to-stereo video generation.<n>Our framework conditions the model on the monocular video input while explicitly supervising the generation with a geometry-aware regularization.<n>To enable large-scale training and evaluation, we curate a high-definition stereo video dataset.
  arXiv  Detail & Related papers  (2025-12-10T06:50:16Z)
• StereoDETR: Stereo-based Transformer for 3D Object Detection [29.652689845108046]
  We propose StereoDETR, an efficient stereo 3D object detection framework based on DETR.<n>It achieves twice the accuracy of monocular approaches, yet its inference speed is only half as fast.<n>It also achieves competitive accuracy on the public KITTI benchmark, setting new state-of-the-art results on pedestrian and cyclist subsets.
  arXiv  Detail & Related papers  (2025-11-24T05:38:31Z)
• S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix [60.060882467801484]
  We present a pose-free and training-free method that leverages an off-the-shelf monocular video generation model to produce immersive 3D videos.<n>Our approach first warps the generated monocular video into pre-defined camera viewpoints using estimated depth information, then applies a novel textitframe matrix inpainting framework.<n>We validate the efficacy of our proposed method by conducting experiments on videos from various generative models, such as Sora, Lumiere, WALT, and Zeroscope.
  arXiv  Detail & Related papers  (2025-08-11T14:50:03Z)
• VoluMe -- Authentic 3D Video Calls from Live Gaussian Splat Prediction [9.570954192915005]
  We present the first method to predict 3D Gaussian reconstructions in real time from a single 2D webcam feed.<n>By conditioning the 3D representation on each video frame independently, our reconstruction faithfully recreates the input video from the captured viewpoint.<n>We show that our method delivers state-of-the-art accuracy in visual quality and stability metrics compared to existing methods.
  arXiv  Detail & Related papers  (2025-07-28T20:07:55Z)
• StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation [56.226630134878995]
  We argue that video depth estimation is not a naive extension of image depth estimation.<n>We introduce StereoDiff, a two-stage video depth estimator that synergizes stereo matching for mainly the static areas with video depth diffusion.
  arXiv  Detail & Related papers  (2025-06-25T18:35:10Z)
• Restereo: Diffusion stereo video generation and restoration [43.208256051997616]
  We introduce a new pipeline that not only generates stereo videos but also enhances both left-view and right-view videos consistently with a single model.<n>Our method can be fine-tuned on a relatively small synthetic stereo video datasets and applied to low-quality real-world videos.
  arXiv  Detail & Related papers  (2025-06-06T12:14:24Z)
• Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion [88.67015254278859]
  We introduce the Mono2Stereo dataset, providing high-quality training data and benchmark to support in-depth exploration of stereo conversion.<n>We conduct an empirical study that yields two primary findings. 1) The differences between the left and right views are subtle, yet existing metrics consider overall pixels, failing to concentrate on regions critical to stereo effects.<n>We introduce a new evaluation metric, Stereo Intersection-over-Union, which harmonizes disparity and achieves a high correlation with human judgments on stereo effect.
  arXiv  Detail & Related papers  (2025-03-28T09:25:58Z)
• StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos [44.51044100125421]
  This paper presents a novel framework for converting 2D videos to immersive stereoscopic 3D, addressing the growing demand for 3D content in immersive experience. Our framework demonstrates significant improvements in 2D-to-3D video conversion, offering a practical solution for creating immersive content for 3D devices like Apple Vision Pro and 3D displays.
  arXiv  Detail & Related papers  (2024-09-11T17:52:07Z)
• Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning [41.30923253467854]
  Temporal features can be complex and diverse.<n>Spatiotemporal models often lean heavily on one type of artifact and ignore the other.<n>Videos are naturally resource-intensive.
  arXiv  Detail & Related papers  (2024-08-30T07:49:57Z)
• DSGN++: Exploiting Visual-Spatial Relation forStereo-based 3D Detectors [60.88824519770208]
  Camera-based 3D object detectors are welcome due to their wider deployment and lower price than LiDAR sensors. We revisit the prior stereo modeling DSGN about the stereo volume constructions for representing both 3D geometry and semantics. We propose our approach, DSGN++, aiming for improving information flow throughout the 2D-to-3D pipeline.
  arXiv  Detail & Related papers  (2022-04-06T18:43:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.