RPNR: Robust-Perception Neural Reshading
Augmented Reality (AR) applications necessitates methods of inserting needed objects into scenes captured by cameras in a way that is coherent with the surroundings. Common AR applications require the insertion of predefined 3D objects with known properties and shape. This simplifies the problem since it is reduced to extracting an illumination model for the object in that scene by understanding the surrounding light sources. However, it is often not the case that we have information about the properties of an object, especially when we depart from a single source image. Our method renders such source fragments in a coherent way with the target surroundings using only these two images. Our pipeline uses a Deep Image Prior (DIP) network based on a U-Net architecture as the main renderer, alongside robust-feature extracting networks that are used to apply needed losses. Our method does not require any pair-labeled data, and no extensive training on a dataset. We compare our method using qualitative metrics to the baseline methods such as Cut and Paste, Cut And Paste Neural Rendering, and Image Harmonization
Code (0)
등록된 구현이 없습니다.
Tasks
Image HarmonizationNeural RenderingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Low-latency Space-time Supersampling for Real-time Rendering
With the rise of real-time rendering and the evolution of display devices, there is a growing demand for post-processing methods that offer high-resolution content in a high frame rate. Existing techniques often suffer f…
ReShader: View-Dependent Highlights for Single Image View-Synthesis
In recent years, novel view synthesis from a single image has seen significant progress thanks to the rapid advancements in 3D scene representation and image inpainting techniques. While the current approaches are able t…
Image InpaintingNovel View SynthesisRobust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification
Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities without any annotations. Recently, clustere…
Person Re-IdentificationPseudo LabelRelationBeyond RGB: Scene-Property Synthesis with Neural Radiance Fields
Comprehensive 3D scene understanding, both geometrically and semantically, is important for real-world applications such as robot perception. Most of the existing work has focused on developing data-driven discriminative…
Data AugmentationEdge DetectionKeypoint DetectionNeRF+4MulT: An End-to-End Multitask Learning Transformer
We propose an end-to-end Multitask Learning Transformer framework, named MulT, to simultaneously learn multiple high-level vision tasks, including depth estimation, semantic segmentation, reshading, surface normal estima…
DecoderDepth EstimationEdge DetectionKeypoint Detection+2