Results 21 to 30 of about 849,712 (309)
Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations [PDF]
Computer Vision and Pattern Recognition, 2021 A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on reconstructing pre-defined 3D representations, e.g.
Mehdi S. M. Sajjadi +12 more
semanticscholar +1 more source
Re-Nerfing: Improving Novel View Synthesis through Novel View Synthesis
, 2023 Code will be released upon ...
Tristram, Felix +3 more
openaire +2 more sources
Two-View Mammogram Synthesis from Single-View Data Using Generative Adversarial Networks
Applied Sciences, 2022 While two-view mammography taking both mediolateral-oblique (MLO) and cranio-caudual (CC) views is the current standard method of examination in breast cancer screening, single-view mammography is still being performed in some countries on women of ...
Asumi Yamazaki, Takayuki Ishida
doaj +1 more source
R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis [PDF]
European Conference on Computer Vision, 2022 Recent research explosion on Neural Radiance Field (NeRF) shows the encouraging potential to represent complex scenes with neural networks. One major drawback of NeRF is its prohibitive inference time: Rendering a single pixel requires querying the NeRF ...
Huan Wang +6 more
semanticscholar +1 more source
Novel View Specification and Synthesis [PDF]
Procedings of the British Machine Vision Conference 2002, 2002 Given a set of real images, Novel View Synthesis (NVS) aims to produce views of a scene that would correspond to that of a virtual camera. There exist many approaches to solving this problem. We consider physically valid NVS methods, in particular those based on epipolar and trifocal transfer.
K. Connor, I. Reid
openaire +1 more source
Novel View Synthesis via Depth-guided Skip Connections [PDF]
2021 IEEE Winter Conference on Applications of Computer Vision (WACV), 2021 We introduce a principled approach for synthesizing new views of a scene given a single source image. Previous methods for novel view synthesis can be divided into image-based rendering methods (e.g. flow prediction) or pixel generation methods. Flow predictions enable the target view to re-use pixels directly, but can easily lead to distorted results.
Solin, Arno, Kannala, Juho, Hou, Yuxin
openaire +3 more sources
STATE: Learning structure and texture representations for novel view synthesis
Computational Visual Media, 2023 Novel viewpoint image synthesis is very challenging, especially from sparse views, due to large changes in viewpoint and occlusion. Existing image-based methods fail to generate reasonable results for invisible regions, while geometry-based methods have ...
Xinyi Jing +5 more
doaj +1 more source
Minimal Warping: Planning Incremental Novel‐view Synthesis [PDF]
Computer Graphics Forum, 2017 AbstractObserving that many visual effects (depth‐of‐field, motion blur, soft shadows, spectral effects) and several sampling modalities (time, stereo or light fields) can be expressed as a sum of many pinhole camera images, we suggest a novel efficient image synthesis framework that exploits coherency among those images.
Leimkuehler, T, Seidel, H-P, Ritschel, T
openaire +3 more sources
MMNeRF: Multi-Modal and Multi-View Optimized Cross-Scene Neural Radiance Fields
IEEE Access, 2023 We present MMNeRF, a simple yet powerful learning framework for highly photo-realistic novel view synthesis by learning Multi-modal and Multi-view features to guide neural radiance fields to a generic model.
Qi Zhang +3 more
doaj +1 more source
Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models [PDF]
IEEE International Conference on Computer Vision, 2023 Novel view synthesis from a single input image is a challenging task, where the goal is to generate a new view of a scene from a desired camera pose that may be separated by a large motion.
Jason J. Yu +3 more
semanticscholar +1 more source