Image Stylization for Robust Features
Local features that are robust to both viewpoint and appearance changes are crucial for many computer vision tasks. In this work we investigate if photorealistic image stylization improves robustness of local features to not only day-night, but also weather and season variations. We show that image stylization in addition to color augmentation is a powerful method of learning robust features. We evaluate learned features on visual localization benchmarks, outperforming state of the art baseline models despite training without ground-truth 3D correspondences using synthetic homographies only. We use trained feature networks to compete in Long-Term Visual Localization and Map-based Localization for Autonomous Driving challenges achieving competitive scores.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingImage StylizationVisual LocalizationSimilar Papers 제목 키워드 기반
Instant Photorealistic Neural Radiance Fields Stylization
We present Instant Neural Radiance Fields Stylization, a novel approach for multi-view image stylization for the 3D scene. Our approach models a neural radiance field based on neural graphics primitives, which use a hash…
GPUImage GenerationImage StylizationPositionZePo: Zero-Shot Portrait Stylization with Faster Sampling
Diffusion-based text-to-image generation models have significantly advanced the field of art content synthesis. However, current portrait stylization methods generally require either model fine-tuning based on examples o…
Image GenerationText to Image GenerationText-to-Image GenerationPortrait Stylization: Artistic Style Transfer with Auxiliary Networks for Human Face Stylization
Today's image style transfer methods have difficulty retaining humans face individual features after the whole stylizing process. This occurs because the features like face geometry and people's expressions are not captu…
Face RecognitionStyle TransferLearning to Stylize Novel Views
We tackle a 3D scene stylization problem - generating stylized images of a scene from arbitrary novel views given a set of images of the same scene and a reference image of the desired style as inputs. Direct solution of…
Novel View SynthesisStyle3D: Attention-guided Multi-view Style Transfer for 3D Object Generation
We present Style3D, a novel approach for generating stylized 3D objects from a content image and a style image. Unlike most previous methods that require case- or style-specific training, Style3D supports instant 3D obje…
3D ReconstructionComputational EfficiencyStyle Transfer