Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 43 for “"neural rendering"”.

  1. Monte-Carlo neural rendering

    Recent advances in neural rendering have achieved high-quality photorealistic scene reconstruction, yet some computational challenges remain. Neural Radiance Fields are slow to train, while 3D Gaussian Splatting depends on heuristic rules, is sensitive to initialization, and fixes rendering quality …

    ubc Repository record for Monte-Carlo neural rendering (opens in a new tab) Download PDF for Monte-Carlo neural rendering (opens in a new tab)

  2. Geometry, Reflectance and Lighting from Neural Rendering

    … reflectance, and lighting estimation through neural rendering to enhance the modeling and understanding of real-world scenes using computer vision. Existing techniques, while show impressive results, have various limitations, such as the need for specialized hardware, laborious manual …

    anu Repository record for Geometry, Reflectance and Lighting from Neural Rendering (opens in a new tab)

  3. Bridging neural rendering and classical computer graphics

    Recent advances in neural rendering have improved both the quality and efficiency of novel view synthesis from multi-view images. In particular, 3D Gaussian Splatting stands out by representing scenes with volumetric primitives and yielding high visual fidelity in real time. Despite these …

    liege Repository record for Bridging neural rendering and classical computer graphics (opens in a new tab) Download PDF for Bridging neural rendering and classical computer graphics (opens in a new tab)

  4. High-Accuracy Intraoperative 3D Reconstruction with Neural Rendering Technology

    … endoscopes. This dissertation argues that recent neural rendering techniques—principally Neural Radiance Fields (NeRF) and 3D Gaussian Splatting—can be redesigned from photorealistic view-synthesis tools into quantitative metrology instruments, recovering near-CT geometric accuracy over the …

    washington Repository record for High-Accuracy Intraoperative 3D Reconstruction with Neural Rendering Technology (opens in a new tab)

  5. Neural Rendering Techniques for Photo-realistic Image Generation and Novel View Synthesis

    … to be able to control different aspects of the rendering process; for example to specify the content and/or style of generated images, camera pose, lighting, ... etc. One challenge to training image generation models is the multi-modal nature of image synthesis. An image with a specific content, …

    maryland Repository record for Neural Rendering Techniques for Photo-realistic Image Generation and Novel View Synthesis (opens in a new tab)

  6. Explicit and implicit warping for accurate human pose estimation and low-latency neural rendering

    Deep neural networks have become an integral part of modern advances in the field of computer vision. However, these solutions are not practical when relying on increasingly large neural networks and diverse datasets to scale. Prior works demonstrate that embedding domain/application-specific …

    ubc Repository record for Explicit and implicit warping for accurate human pose estimation and low-latency neural rendering (opens in a new tab) Download PDF for Explicit and implicit warping for accurate human pose estimation and low-latency neural rendering (opens in a new tab)

  7. TransFURmer: Hair and Fur rendering using SwinIR - Transformer-based Neural Rendering of Hair and Fur using SwinIR

    While ray tracing algorithms offer photorealistic rendering of hair and fur, their high computational cost makes them unfeasible for real-time applications. Conversely, fast rendering techniques such as rasterization fail to capture accurate lighting effects and high-frequency details. This thesis …

    chalmers Repository record for TransFURmer: Hair and Fur rendering using SwinIR - Transformer-based Neural Rendering of Hair and Fur using SwinIR (opens in a new tab)

  8. 3D CONTENT CREATION FROM IMAGES

    … driven by building alternative differentiable neural rendering pipelines that exploit the power of machine learning. In this dissertation, we first present a method that seamlessly retargets photogrammetry pipelines developed for ground-level photos to satellite imageries. We then show a neural …

    cornell Repository record for 3D CONTENT CREATION FROM IMAGES (opens in a new tab)

  9. Radiance transfer prediction for real-time rendering using neural networks and geometric algebra

    … (PRT) has long been a cornerstone of real-time rendering, enabling high-fidelity global illumination under complex lighting. However, traditional PRT suffers from prohibitive precomputation costs, limited scalability to high-resolution meshes, and impracticality for dynamic or animated …

    greece Repository record for Radiance transfer prediction for real-time rendering using neural networks and geometric algebra (opens in a new tab)

  10. Photorealistic 3D Mapping of Real-World Scenes: Methods and Applications

    … limitations in sensing, reconstruction accuracy, rendering fidelity, and data acquisition and synthesis efficiency. We advance photorealistic 3D mapping through three interconnected research goals: sensing and perception, mapping, and generation. The first part of our dissertation focuses on …

    maryland Repository record for Photorealistic 3D Mapping of Real-World Scenes: Methods and Applications (opens in a new tab)

  11. Efficient Text-Driven 3D Scene Editing Based on Gaussian Splatting

    … editing has advanced with diffusion models and neural rendering. While Neural Radiance Fields (NeRF) excel at 3D reconstruction and novel view synthesis, they face key challenges: computational inefficiency, multi-view inconsistency, and poor handling of motion blur. To overcome these …

    ottawa-retro Repository record for Efficient Text-Driven 3D Scene Editing Based on Gaussian Splatting (opens in a new tab)

  12. Towards Zero Bottlenecks for Scaling Autonomous Driving

    … years and conditions (III), and developing a neural rendering method that enables scalable generation of realistic synthetic data (IV). Finally, to enable scalable safety testing, we introduce a closed-loop neural simulator that transforms ordinary driving scenarios into challenging …

    lund Repository record for Towards Zero Bottlenecks for Scaling Autonomous Driving (opens in a new tab) Download PDF for Towards Zero Bottlenecks for Scaling Autonomous Driving (opens in a new tab)

  13. Intelligent Treadmill Control and Holographic Rendering for Accessible Rehabilitation

    … solutions. We adopted advanced neural rendering techniques to build a low-cost 3D patient reconstruction pipeline to enhance remote patient monitoring and engagement. Through these innovations, this dissertation contributes to making rehabilitation more accessible, affordable, …

    alabama Repository record for Intelligent Treadmill Control and Holographic Rendering for Accessible Rehabilitation (opens in a new tab)

  14. Gaussian shadow casting for neural characters

    … and creating 3D animatable avatars through neural rendering have obtained impressive rendering results, even when learning from monocular video data. These neural characters, while achieving highly detailed geometry and texture reconstruction, bake lighting and shadow information into the …

    ubc Repository record for Gaussian shadow casting for neural characters (opens in a new tab) Download PDF for Gaussian shadow casting for neural characters (opens in a new tab)

  15. Gauss-Newton Optimizer for 3D Gaussian Splatting Reconstruction

    Recent advancements in neural rendering have enabled highly realistic and efficient representations of 3D scenes from multi-view images. Among these, 3D Gaussian Splatting (3DGS) has emerged as a promising technique that represents scenes using a collection of 3D Gaussian primitives. Since it is a …

    chalmers Repository record for Gauss-Newton Optimizer for 3D Gaussian Splatting Reconstruction (opens in a new tab)

  16. Harnessing Scattered Light Transport: Computational Imaging Systems for One-Way Visibility and Polarimetric and Time-of-flight Inverse Rendering

    … This may be insufficient for inverse rendering, i.e. retrieval of geometric and optical properties of the target from captured images. The first part of this thesis explores how time-of-flight measurements can improve the spatial resolution for imaging through volumetric-scattering …

    rice Repository record for Harnessing Scattered Light Transport: Computational Imaging Systems for One-Way Visibility and Polarimetric and Time-of-flight Inverse Rendering (opens in a new tab)

  17. Neural Representation for Camera Models and Dynamic Scenes

    … camera models and 3D scenes using deep neural networks. The first part of this dissertation focuses on the development of a neural lens model, which simplifies the process of pre-capture camera calibration and refines camera parameters during 3D reconstruction. The proposed method …

    cornell Repository record for Neural Representation for Camera Models and Dynamic Scenes (opens in a new tab)

  18. Connecting the Dots: Combining Points and Lines for more Robust and Accurate Local Features

    … localization and mapping, 3D reconstruction, and neural rendering, to obtain a highly accurate 3D geometry of a scene. Thus, local features are expected to be accurate, but also to be efficient and versatile to different tasks and conditions. This thesis explores some of the limitations of modern …

    ethz Repository record for Connecting the Dots: Combining Points and Lines for more Robust and Accurate Local Features (opens in a new tab)

  19. Realistically Editing Indoor Scenes

    … floor, doors, windows). I present an inverse rendering framework to use the high dynamic range data to simultaneously infer light intensity distributions and diffuse reflectances across an entire indoor scene that enables realistic visualizations of emptying, refurnishing, and relighting a …

    washington Repository record for Realistically Editing Indoor Scenes (opens in a new tab)

  20. Exploring explicit models for geometric point cloud learning

    … challenging to process point clouds with deep neural networks because of their irregular data structure, the difficulty in encoding contextual information from nearby points, and the large compute requirement that is typically required. This thesis addresses these challenges by enforcing …

    ubc Repository record for Exploring explicit models for geometric point cloud learning (opens in a new tab) Download PDF for Exploring explicit models for geometric point cloud learning (opens in a new tab)

Page 1 of 3