Segmenting Scenes by Matching Image Composites
In this paper, we investigate how similar images sharing the same global description can help with unsupervised scene segmentation in an image. In contrast to recent work in semantic alignment of scenes, we allow an input image to be explained by partial matches of similar scenes. This allows for a better explanation of the input scenes. We perform MRF-based segmentation that optimizes over matches, while respecting boundary information. The recovered segments are then used to re-query a large database of images to retrieve better matches for the target region. We show improved performance in detecting occluding boundaries over previous methods on data gathered from the LabelMe database.
Code (0)
등록된 구현이 없습니다.
Tasks
Scene SegmentationSegmentationSimilar Papers 제목 키워드 기반
AI-Driven Stylization of 3D Environments
In this system, we discuss methods to stylize a scene of 3D primitive objects into a higher fidelity 3D scene using novel 3D representations like NeRFs and 3D Gaussian Splatting. Our approach leverages existing image sty…
Image StylizationImage to 3DStyleSplat: 3D Object Style Transfer with Gaussian Splatting
Recent advancements in radiance fields have opened new avenues for creating high-quality 3D assets and scenes. Style transfer can enhance these 3D assets with diverse artistic styles, transforming creative expression. Ho…
ObjectStyle TransferComFusion: Personalized Subject Generation in Multiple Specific Scenes From Single Image
Recent advancements in personalizing text-to-image (T2I) diffusion models have shown the capability to generate images based on personalized visual concepts using a limited number of user-provided examples. However, thes…
ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion
We present ZeroComp, an effective zero-shot 3D object compositing approach that does not require paired composite-scene images during training. Our method leverages ControlNet to condition from intrinsic images and combi…
Matching Anything by Segmenting Anything
The robust association of the same objects across video frames in complex scenes is crucial for many applications, especially Multiple Object Tracking (MOT). Current methods predominantly rely on labeled domain-specific …
Domain GeneralizationMultiple Object TrackingObjectObject Tracking+1