paper-with-me

홈 › Papers

Semantic View Synthesis

2020-08-24 · ECCV 2020 8 · Hsin-Ping Huang, Hung-Yu Tseng, Hsin-Ying Lee, Jia-Bin Huang

We tackle a new problem of semantic view synthesis -- generating free-viewpoint rendering of a synthesized scene using a semantic label map as input. We build upon recent advances in semantic image synthesis and view synthesis for handling photographic image content generation and view extrapolation. Direct application of existing image/view synthesis methods, however, results in severe ghosting/blurry artifacts. To address the drawbacks, we propose a two-step approach. First, we focus on synthesizing the color and depth of the visible surface of the 3D scene. We then use the synthesized color and depth to impose explicit constraints on the multiple-plane image (MPI) representation prediction process. Our method produces sharp contents at the original view and geometrically consistent renderings across novel viewpoints. The experiments on numerous indoor and outdoor images show favorable results against several strong baselines and validate the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2008.10598

Code (1)

hhsinping/svs 공식 구현 pytorch

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Generative View Synthesis: From Single-view Semantics to Novel-view Images

2020-08-20 · NeurIPS 2020 12 · Tewodros Habtegebrial, Varun Jampani, Orazio Gallo, Didier Stricker

Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single…

Image GenerationTranslation

Retrieval-guided Cross-view Image Synthesis

2024-11-29 · Hongji Yang, Yiru Li, Yingying Zhu

Information retrieval techniques have demonstrated exceptional capabilities in identifying semantic similarities across diverse domains through robust feature representations. However, their potential in guiding synthesi…

Contrastive LearningDiversityImage GenerationInformation Retrieval+3

CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion

2023-07-16 · ICCV 2023 1 · Haotian Dong, Enhui Ma, Lubo Wang, Miaohui Wang 외

Semantic scene completion (SSC) requires an accurate understanding of the geometric and semantic relationships between the objects in the 3D scene for reasoning the occluded objects. The popular SSC methods voxelize the …

Object

Painting 3D Nature in 2D: View Synthesis of Natural Scenes from a Single Semantic Mask

2023-02-14 · CVPR 2023 1 · Shangzhan Zhang, Sida Peng, Tianrun Chen, Linzhan Mou 외

We introduce a novel approach that takes a single semantic mask as input to synthesize multi-view consistent color images of natural scenes, trained with a collection of single images from the Internet. Prior works on 3D…

3D-Aware Image SynthesisImage Generation

SPC-GS: Gaussian Splatting with Semantic-Prompt Consistency for Indoor Open-World Free-view Synthesis from Sparse Inputs

2025-03-16 · CVPR 2025 1 · Guibiao Liao, Qing Li, Zhenyu Bao, Guoping Qiu 외

3D Gaussian Splatting-based indoor open-world free-view synthesis approaches have shown significant performance with dense input images. However, they exhibit poor performance when confronted with sparse inputs, primaril…

Semantic SegmentationVideo Generation