Spaces:
Running
Running
| <html> | |
| <head> | |
| <meta charset="utf-8"> | |
| <meta name="description" | |
| content="StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space"> | |
| <meta name="keywords" content="stereo generation, diffusion models, image processing, computer vision"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |
| <meta name="twitter:card" content="summary"> | |
| <meta name="twitter:image:src" content="http://marigoldmonodepth.github.io/images/marigold_logo_square.jpg"> | |
| <meta name="twitter:title" content="StereoSpace"> | |
| <meta name="twitter:description" content="StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space"> | |
| <meta name="twitter:creator" content="@AntonObukhov1"> | |
| <title>StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space</title> | |
| <!-- Google tag (gtag.js) --> | |
| <script async src="https://www.googletagmanager.com/gtag/js?id=G-1FWSVCGZTG"></script> | |
| <script> | |
| window.dataLayer = window.dataLayer || []; | |
| function gtag() { | |
| dataLayer.push(arguments); | |
| } | |
| gtag('js', new Date()); | |
| gtag('config', 'G-1FWSVCGZTG'); | |
| </script> | |
| <!-- Huggingface Space Header --> | |
| <script type="module"> | |
| import { init } from "https://cdn.jsdelivr.net/npm/@huggingface/space-header/+esm"; | |
| init("prs-eth/stereospace_web"); | |
| </script> | |
| <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" | |
| rel="stylesheet"> | |
| <link rel="stylesheet" href="./css/bulma.min.css"> | |
| <link rel="stylesheet" href="./css/bulma-carousel.min.css"> | |
| <link rel="stylesheet" href="./css/bulma-slider.min.css"> | |
| <link rel="stylesheet" href="./css/twentytwenty.css"> | |
| <link rel="stylesheet" href="./css/index.css"> | |
| <link rel="icon" href="./images/favicon.svg"> | |
| <link rel="stylesheet" href="./css/comparison-widget.css?v=1"> | |
| <script src="./js/jquery-3.2.1.min.js"></script> | |
| <script src="./js/jquery.event.move.js"></script> | |
| <script src="./js/jquery.twentytwenty.js"></script> | |
| <script src="./js/bulma-carousel.min.js"></script> | |
| <script src="./js/bulma-slider.min.js"></script> | |
| <script src="./js/fontawesome.all.min.js"></script> | |
| <script src="./js/comparison-widget.js"></script> | |
| <!--MathJax--> | |
| <script> | |
| window.MathJax = { | |
| tex: { | |
| inlineMath: [['$', '$'], ['\\(', '\\)']] | |
| }, | |
| svg: { | |
| fontCache: 'global' | |
| } | |
| }; | |
| </script> | |
| <script type="text/javascript" id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script> | |
| </head> | |
| <body> | |
| <section class="hero"> | |
| <div class="hero-body"> | |
| <div class="container is-max-desktop"> | |
| <div class="columns is-centered"> | |
| <div class="column has-text-centered"> | |
| <h1 class="title is-1 publication-title">StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space</h1> | |
| <div class="is-size-5 publication-authors"> | |
| <span class="author-block"><a href="https://scholar.google.com/citations?user=5tfQSGkAAAAJ" target="_blank">Tjark Behrens</a><sup>1</sup>,</span> | |
| <span class="author-block"><a href="https://www.obukhov.ai/" target="_blank">Anton Obukhov</a><sup>3</sup>,</span> | |
| <span class="author-block"><a href="https://www.kebingxin.com/" target="_blank">Bingxin Ke</a><sup>1</sup>,</span> | |
| <span class="author-block"><a href="https://fabiotosi92.github.io/" target="_blank">Fabio Tosi</a><sup>2</sup>,</span> | |
| <span class="author-block"><a href="https://mattpoggi.github.io/" target="_blank">Matteo Poggi</a><sup>2</sup>,</span> | |
| <span class="author-block"><a href="https://scholar.google.com/citations?user=FZuNgqIAAAAJ" target="_blank">Konrad Schindler</a><sup>1</sup></span> | |
| </div> | |
| <div class="is-size-5 publication-authors"> | |
| <span class="author-block"><sup>1</sup>ETH Zürich</span> | |
| <span class="author-block"><sup>2</sup>University of Bologna</span> | |
| <span class="author-block"><sup>3</sup>HUAWEI Bayer Lab</span> | |
| </div> | |
| <div class="column has-text-centered"> | |
| <div class="publication-links"> | |
| <!-- Paper --> | |
| <span class="link-block"> | |
| <a href="https://arxiv.org/abs/2512.10959" target="_blank" rel="noopener noreferrer" | |
| class="external-link button is-normal is-rounded is-dark"> | |
| <span class="icon"> | |
| <i class="fas fa-file-pdf" style="color: orangered"></i> | |
| </span> | |
| <span>Paper</span> | |
| </a> | |
| </span> | |
| <!-- Code --> | |
| <span class="link-block"> | |
| <a href="https://github.com/prs-eth/stereospace" target="_blank" rel="noopener noreferrer" class="external-link button is-normal is-rounded is-dark"> | |
| <span class="icon"> | |
| <i class="fab fa-github"></i> | |
| </span> | |
| <span> | |
| Code | |
| </span> | |
| </a> | |
| </span> | |
| <!-- Demo --> | |
| <span class="link-block"> | |
| <a href="https://hf.co/spaces/toshas/stereospace" target="_blank" rel="noopener noreferrer" class="external-link button is-normal is-rounded is-dark"> | |
| <span class="icon"> | |
| 🤗 | |
| </span> | |
| <span> | |
| Demo | |
| </span> | |
| </a> | |
| </span> | |
| <!-- Model --> | |
| <span class="link-block"> | |
| <a href="https://hf.co/prs-eth/stereospace-v1-0" target="_blank" rel="noopener noreferrer" class="external-link button is-normal is-rounded is-dark"> | |
| <span class="icon"> | |
| 🤗 | |
| </span> | |
| <span> | |
| Model | |
| </span> | |
| </a> | |
| </span> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="hero teaser"> | |
| <div class="is-max-desktop"> | |
| <div class="hero-body"> | |
| <!-- Desktop version (full-width image) --> | |
| <div id="teaser-desktop"> | |
| <img src="./images/teaser.jpg" alt="Teaser image" style="width:100%;"/> | |
| <div class="content has-text-justified"> | |
| We present <span class="methodname">StereoSpace</span>, a method for generating stereo from monocular images. | |
| <b>Left</b>: Built on a foundational LDM, our framework efficiently leverages learned priors for end-to-end view synthesis. The target baseline in world units acts as conditioning for precise view control. | |
| Images featuring the dragon are illustrative examples. <b>Right</b>: Implicit scene understanding allows us to tackle the most complex cases | |
| where geometry cues alone are insufficient for novel view synthesis. Best viewed zoomed-in. Legend: <i>squares</i> — warping, <i>circles</i> — breaks, <i>lines</i> — bends, | |
| <i>arrows</i> — ghosting. StereoSpace consistently outperforms recent monocular competition, including generative 3DGS models like Lyra. | |
| </div> | |
| </div> | |
| <!-- Mobile version (two halves) --> | |
| <div id="teaser-mobile"> | |
| <div class="teaser-half teaser-half-left mb-4"> | |
| <img src="./images/teaser.jpg" alt="Teaser left half"> | |
| </div> | |
| <div class="content has-text-justified"> | |
| We present <span class="methodname">StereoSpace</span>, a method for generating stereo from monocular images. | |
| Built on a foundational LDM, our framework efficiently leverages learned priors for end-to-end view synthesis. The target baseline in world units acts as conditioning for precise view control. | |
| Images featuring the dragon are illustrative examples. | |
| </div> | |
| <div class="teaser-half teaser-half-right mb-4"> | |
| <img src="./images/teaser.jpg" alt="Teaser right half"> | |
| </div> | |
| <div class="content has-text-justified"> | |
| Implicit scene understanding allows us to tackle the most complex cases | |
| where geometry cues alone are insufficient for novel view synthesis. Best viewed zoomed-in. Legend: <i>squares</i> — warping, <i>circles</i> — breaks, <i>lines</i> — bends, | |
| <i>arrows</i> — ghosting. StereoSpace consistently outperforms recent monocular competition, including generative 3DGS models like Lyra. | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="section pt-0"> | |
| <div class="container is-max-desktop"> | |
| <!-- Abstract. --> | |
| <div class="columns is-centered has-text-centered"> | |
| <div class="column is-four-fifths"> | |
| <h2 class="title is-3">Abstract</h2> | |
| <div class="content has-text-justified"> | |
| <p> | |
| <span class="methodname">StereoSpace</span> is a diffusion-based framework for monocular-to-stereo synthesis that models geometry purely through viewpoint conditioning, | |
| without explicit depth or warping. A canonical rectified space and the conditioning guide the generator to infer correspondences and fill disocclusions | |
| end-to-end. To ensure fair and leakage-free evaluation, we introduce an end-to-end protocol that excludes any ground truth or proxy geometry estimates | |
| at test time. The protocol emphasizes metrics reflecting downstream relevance: iSQoE for perceptual comfort and MEt3R for geometric consistency. | |
| StereoSpace surpasses other methods from the warp & inpaint, latent-warping, and warped-conditioning categories, achieving sharp parallax and strong | |
| robustness on layered and non-Lambertian scenes. This establishes viewpoint-conditioned diffusion as a scalable, depth-free solution for stereo generation. | |
| </p> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="section pt-0 pb-4"> | |
| <div class="container is-max-desktop"> | |
| <div class="columns is-centered has-text-centered"> | |
| <div class="column is-four-fifths"> | |
| <h2 class="title is-3">Gallery</h2> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Results Carousel. --> | |
| <section class="hero is-light is-small mt-4"> | |
| <div class="hero-body"> | |
| <div class="content has-text-justified"> | |
| <p> | |
| <span class="methodname">StereoSpace</span> shows strong generalization on in-the-wild imagery. | |
| The examples in this gallery include challenging reflective surfaces that never appear during training, | |
| yet the model produces consistent, high-quality results, indicating robust out-of-distribution behavior. | |
| We show the outputs in two common stereo formats: anaglyph and side-by-side, using the two components below. | |
| </p> | |
| <p> | |
| Use anaglyph glasses to watch the results of <span class="methodname">StereoSpace</span> in stereo: | |
| </p> | |
| </div> | |
| <div id="results-carousel-horizontal" class="carousel results-carousel"> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/bakery_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/bakery_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/cafe_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/cafe_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/car_wheel_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/car_wheel_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/dog_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/dog_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/entrance_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/entrance_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/misty_train_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/misty_train_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/museum_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/museum_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/park_cart_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/park_cart_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/pharaoh_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/pharaoh_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/phone_booth_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/phone_booth_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/store_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/store_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="twentytwenty-container twentytwenty-container-top"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/store_front_source.png"> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/store_front_anaglyph.png"> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="hero is-light is-small"> | |
| <div class="hero-body pt-0"> | |
| <div class="content has-text-justified"> | |
| <p> | |
| Use VR or any SBS (side-by-side) compatible viewer to watch the results of <span class="methodname">StereoSpace</span> in stereo: | |
| </p> | |
| </div> | |
| <div id="results-carousel-vertical" class="carousel results-carousel"> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/bakery_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/cafe_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/car_wheel_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/dog_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/entrance_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/misty_train_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/museum_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/park_cart_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/pharaoh_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/phone_booth_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/store_sbs.png"> | |
| </div> | |
| </div> | |
| <div class="twoitem"> | |
| <div class="cmpcontent"> | |
| <img alt="" src="./images/comparison/store_front_sbs.png"> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Baseline Comparison Title --> | |
| <section class="section pt-6 pb-4"> | |
| <div class=" is-max-desktop"> | |
| <div class="columns is-centered has-text-centered"> | |
| <div class="column is-four-fifths"> | |
| <h2 class="title is-3">Qualitative Comparison with Other Recent Methods</h2> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Combined Gallery and Comparison Widget with Light Background --> | |
| <section class="hero is-light is-small mt-4"> | |
| <div class="hero-body"> | |
| <div class="is-max-desktop"> | |
| <div class="content has-text-justified"> | |
| <p> | |
| The component below provides a qualitative comparison with several recent methods on the same scenes. | |
| You can switch between scenes using the previews at the top and compare methods by selecting them with the buttons inside the main view. | |
| </p> | |
| </div> | |
| <!-- Image Gallery --> | |
| <div class="ws-gallery-grid mb-5"> | |
| <div class="ws-gallery-item is-active" data-scene="215"> | |
| <img src="./images/teaser_subfigures/215/tgt.png" alt="215" /> | |
| </div> | |
| <div class="ws-gallery-item" data-scene="249"> | |
| <img src="./images/teaser_subfigures/249/tgt.png" alt="249" /> | |
| </div> | |
| <div class="ws-gallery-item" data-scene="252"> | |
| <img src="./images/teaser_subfigures/252/tgt.png" alt="252" /> | |
| </div> | |
| <div class="ws-gallery-item" data-scene="285"> | |
| <img src="./images/teaser_subfigures/285/tgt.png" alt="285" /> | |
| </div> | |
| <div class="ws-gallery-item" data-scene="297"> | |
| <img src="./images/teaser_subfigures/297/tgt.png" alt="297" /> | |
| </div> | |
| </div> | |
| <!-- Comparison Widget --> | |
| <div class="columns is-variable is-2-desktop"> | |
| <!-- StereoSpace vs Baseline comparison with slider --> | |
| <div class="column"> | |
| <div class="ws-card"> | |
| <div class="ws-card-body ws-card-body-relative"> | |
| <div class="twentytwenty-container twentytwenty-container-top" id="ws-comparison-slider"> | |
| <div class="cmpcontent"> | |
| <img | |
| id="ws-image-left" | |
| src="./images/teaser_subfigures/215/tgt.png" | |
| alt="Ground Truth" | |
| /> | |
| </div> | |
| <div class="cmpcontent"> | |
| <img | |
| id="ws-image-right" | |
| src="./images/teaser_subfigures/215/stereospace.png" | |
| alt="StereoSpace (ours)" | |
| /> | |
| </div> | |
| </div> | |
| <!-- Model selector for baseline comparison --> | |
| <div class="ws-model-selector-overlay"> | |
| <button class="ws-model-pill is-active" data-model="stereospace">StereoSpace (ours)</button> | |
| <button class="ws-model-pill" data-model="lyra">Lyra</button> | |
| <button class="ws-model-pill" data-model="genstereo">GenStereo</button> | |
| <button class="ws-model-pill" data-model="stereodiffusion">StereoDiffusion</button> | |
| <button class="ws-model-pill" data-model="zerostereo">ZeroStereo</button> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="section"> | |
| <div class="container is-max-desktop"> | |
| <!-- Method. --> | |
| <div class="columns is-centered has-text-centered"> | |
| <div class="column is-four-fifths"> | |
| <h2 class="title is-3">Our Approach</h2> | |
| <div class="content has-text-justified"> | |
| <h3 class="title has-text-centered mt-4"> | |
| Idea | |
| </h3> | |
| <p> | |
| Unlike recent methods grouped under "warp-and-inpaint", "latent warping", or "warped conditioning", each relying | |
| on explicit monocular geometry estimates that are difficult and error-prone, we instead let the foundation | |
| diffusion model infer 3D structure implicitly and train stereo generation end-to-end. | |
| The resulting model outperforms all these categories and even surpasses Lyra, a strong generative 3DGS-based competitor. | |
| Qualitative examples are shown in the slider above. | |
| </p> | |
| <h3 class="title has-text-centered mt-4"> | |
| Contributions | |
| </h3> | |
| <ul> | |
| <li> | |
| Single-image conditional generation of counterpart views, free from explicit geometric shortcuts; | |
| </li> | |
| <li> | |
| End-to-end training procedure for efficient transfer of the rich task-agnostic foundation prior to the task at hand; | |
| </li> | |
| <li> | |
| A novel perceptual and geometry-aware evaluation. | |
| </li> | |
| </ul> | |
| <h3 class="title has-text-centered mt-4"> | |
| Model Architecture for End-to-End View Synthesis | |
| </h3> | |
| <p> | |
| To produce the right view, our model uses a dual U-Net initialized from Stable Diffusion v2.0. | |
| The top branch operates on the source view latent as well as the viewpoint condition. | |
| The target baseline is encoded similarly and is concatenated with the latent code of the counterpart view. | |
| Latent and pixel-space losses supervise fine-tuning, wherein target view synthesis leverages source view features through end-to-end cross attention. | |
| Red arrows denote operations at training time only. | |
| </p> | |
| <img id="method_inference" src="./images/method.jpg" alt="Method"/> | |
| <h3 class="title has-text-centered mt-5"> | |
| Quantitative Comparison with Other Recent Methods | |
| </h3> | |
| <p> | |
| We compare the baselines using two complementary metrics: iSQoE, which reflects stereo viewing comfort and | |
| perceptual coherence, and MEt3R, which captures geometric consistency across the rendered views. | |
| Interpreted together, these metrics make the performance differences clear. | |
| Diffusion-based inpainting methods score worse in both perceptual and geometric metrics, reflecting their | |
| tendency toward smooth but structurally unreliable completions. Warping-based models improve geometry but | |
| still struggle in occluded regions, which the metrics reveal. Depth-conditioned GenStereo performs more | |
| stably, especially on simpler scenes. Across datasets, StereoSpace is the only method improving both | |
| perceptual comfort and geometric consistency simultaneously, indicating that integrating geometry directly | |
| into generation in an end-to-end fashion is most effective. | |
| </p> | |
| <img id="comparison" src="./images/tables.png" alt="Quantitative Comparison with Other Recent Methods"/> | |
| <p class="mt-4 mb-0 pb-0"> | |
| Refer to the pdf paper linked above for more details on qualitative, quantitative, and ablation studies. | |
| </p> | |
| </div> | |
| </div> | |
| </div> | |
| <!--/ Method. --> | |
| </div> | |
| </section> | |
| <script> | |
| $(window).on('load', function() { | |
| bulmaCarousel.attach('#results-carousel-horizontal', { | |
| slidesToScroll: 1, | |
| slidesToShow: 3, | |
| loop: true, | |
| autoplay: true, | |
| }); | |
| bulmaCarousel.attach('#results-carousel-vertical', { | |
| slidesToScroll: 1, | |
| slidesToShow: 1, | |
| loop: true, | |
| autoplay: true, | |
| }); | |
| bulmaCarousel.attach('#results-carousel-testimonials', { | |
| slidesToScroll: 1, | |
| slidesToShow: 3, | |
| loop: true, | |
| autoplay: true, | |
| }); | |
| $(".twentytwenty-container-top").twentytwenty({ | |
| before_label: 'Input', | |
| after_label: 'StereoSpace (ours)', | |
| default_offset_pct: 0.4, | |
| }); | |
| // Initialize comparison widget slider with different labels | |
| $("#ws-comparison-slider").twentytwenty({ | |
| before_label: 'StereoSpace (ours)', | |
| after_label: 'Ground Truth', | |
| default_offset_pct: 0.33, | |
| }); | |
| $('.results-carousel').css({ | |
| 'max-height': '2000px', | |
| 'visibility': 'visible' | |
| }); | |
| }); | |
| </script> | |
| <section class="section mt-0 pt-0" id="BibTeX"> | |
| <div class="container is-max-desktop content"> | |
| <h2 class="title">Citation</h2> | |
| <pre class="selectable"> | |
| @misc{behrens2025stereospace, | |
| title = {StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space}, | |
| author = {Tjark Behrens and Anton Obukhov and Bingxin Ke and Fabio Tosi and Matteo Poggi and Konrad Schindler}, | |
| year = {2025}, | |
| eprint = {2512.10959}, | |
| archivePrefix= {arXiv}, | |
| primaryClass = {cs.CV}, | |
| url = {https://arxiv.org/abs/2512.10959}, | |
| } | |
| </pre> | |
| </div> | |
| </section> | |
| <footer class="footer pt-4 pb-0"> | |
| <div class="container"> | |
| <div class="columns is-centered"> | |
| <div class="column is-8"> | |
| <div class="content"> | |
| <p> | |
| Website template based on | |
| <a href="https://github.com/nerfies/nerfies.github.io"> | |
| Nerfies | |
| </a> | |
| and licensed under | |
| <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"> | |
| CC-BY-SA-4.0 | |
| </a>. | |
| </p> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </footer> | |
| </body> | |
| </html> | |