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 14 of 14 for “"Novel View Synthesis"”.

  1. Novel View Synthesis from Casually Recorded Videos

    Generating new, photorealistic views of a scene given only a single video is a difficult task that computer vision researchers have worked on for decades. This problem has recently seen a resurgence in interest due to its potential application in areas such as virtual reality. However, current …

    mit Repository record for Novel View Synthesis from Casually Recorded Videos (opens in a new tab)

  2. Generalizable and Efficient Novel View Synthesis with Perceptual Foundations

    Recent advancements in novel view synthesis have demonstrated remarkable potential. Although these methods are capable of generating visually compelling novel views, their reliance on per-scene retraining severely limits their scalability and practical applications. The central goal of this …

    cambridge Repository record for Generalizable and Efficient Novel View Synthesis with Perceptual Foundations (opens in a new tab)

  3. Improve OpenMVG and create a novel algorithm for novel view synthesis from point clouds

    … reconstruction software OpenMVG and to create a novel algorithm to render photorealistic images from new views given a photo collection and 3D point cloud. First, the original OpenMVG is parallelized using GPU and its data structure is optimized. Moreover, we integrated the MatchMiner algorithm …

    uiuc Repository record for Improve OpenMVG and create a novel algorithm for novel view synthesis from point clouds (opens in a new tab)

  4. Hardware Acceleration for Real-Time Compression of 3D Gaussians

    3D Gaussian Splatting (3DGS) is a technique for novel view synthesis, where images of a scene from a specific viewpoint are generated using images from different viewpoints, that has gained popularity for its reduced computational overhead, resulting in faster training and rendering times compared …

    mit Repository record for Hardware Acceleration for Real-Time Compression of 3D Gaussians (opens in a new tab)

  5. Mesh Differentiable Rendering for Real-World Scenes

    … as an effective tool for 3D reconstruction and novel view synthesis. Most state-of-the-art differentiable rendering methods use purpose-built renderers to optimize specialized, nonstandard 3D representations. However, most downstream applications of differentiable rendering rely on 3D meshes, …

    mit Repository record for Mesh Differentiable Rendering for Real-World Scenes (opens in a new tab)

  6. Neural Representation for robotics

    … demonstrated exceptional capabilities in Novel View Synthesis (NVS), effectively handling many scenarios where conventional depth cameras struggle. Moreover, unlike traditional methods requiring pre-existing CAD models, neural representations can be generated directly from object images, …

    trento Repository record for Neural Representation for robotics (opens in a new tab)

  7. Diver: real-time and accurate neural radiance fields with deterministic integration for volume rendering

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms

    uiuc Repository record for Diver: real-time and accurate neural radiance fields with deterministic integration for volume rendering (opens in a new tab)

  8. Harnessing data priors to mitigate 3D data scarcity

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms

    uiuc Repository record for Harnessing data priors to mitigate 3D data scarcity (opens in a new tab)

  9. Learning to handle occlusion for motion analysis and view synthesis

    … example, when we see a car gradually blocks our view of a human figure, we know that either the car or the human is moving. We also know that the human behind the car will be visible again if we move to other positions. As many vision-based intelligent systems need to handle and react to visual …

    vt Repository record for Learning to handle occlusion for motion analysis and view synthesis (opens in a new tab)

  10. Algorithms & Systems for Differentiable Graphics Programming

    … learning-based approaches in inverse rendering, novel-view synthesis, data & compute efficient rendering, and even 3D generative models. We see great advances in performance & fidelity when mixing classical wisdom from existing primitives like meshes and textures, and novel primitives like tiny …

    mit Repository record for Algorithms & Systems for Differentiable Graphics Programming (opens in a new tab)

  11. Adapting Single-View View Synthesis with Multiplane Images for 3D Video Chat

    … communities. In this thesis, we have employed novel view synthesis in attempting to turn one-on-one video chatting into 3D. We have tuned the learning pipeline of Tucker and Snavely's <em>single-view</em> view synthesis <a href="https://single-view-mpi.github.io/" target="_blank">paper</a> — by …

    calpoly Repository record for Adapting Single-View View Synthesis with Multiplane Images for 3D Video Chat (opens in a new tab)

  12. Multi-bounce Returns for Specular Surface Mapping from Consumer-grade Flash LiDAR

    … on applications such as segmentation and novel view synthesis. Our method can be combined with these state-of-the-art learned-based model, enhancing its robustness by discerning ambiguous scenarios. In general, this approach can map various specular surfaces like mirrors and glasses, …

    mit Repository record for Multi-bounce Returns for Specular Surface Mapping from Consumer-grade Flash LiDAR (opens in a new tab)

  13. Discovering, Learning, and Exploiting Visual Cues

    … hidden parts of the scene. We then exploit multi-view reflections to convert household objects into radiance-field cameras that can image the world from the object's perspective in 5D. This enables applications of occlusion imaging, beyond field-of-view novel-view synthesis, and depth estimation …

    mit Repository record for Discovering, Learning, and Exploiting Visual Cues (opens in a new tab)

  14. Principled Methods for Advancing Generative Machine Learning

    With the aim of generating novel data beyond collected samples, generative machine learning (ML) has become one of the most actively explored research areas in recent years, witnessing a series of groundbreaking advances. In computer vision (CV), diffusion models mark a major milestone — they can …

    cambridge Repository record for Principled Methods for Advancing Generative Machine Learning (opens in a new tab)