SePaint: Semantic Map Inpainting via Multinomial Diffusion
Prediction beyond partial observations is crucial for robots to navigate in unknown environments because it can provide extra information regarding the surroundings beyond the current sensing range or resolution. In this work, we consider the inpainting of semantic Bird's-Eye-View maps. We propose SePaint, an inpainting model for semantic data based on generative multinomial diffusion. To maintain semantic consistency, we need to condition the prediction for the missing regions on the known regions. We propose a novel and efficient condition strategy, Look-Back Condition (LB-Con), which performs one-step look-back operations during the reverse diffusion process. By doing so, we are able to strengthen the harmonization between unknown and known parts, leading to better completion performance. We have conducted extensive experiments on different datasets, showing our proposed model outperforms commonly used interpolation methods in various robotic applications.
Code (0)
등록된 구현이 없습니다.
Tasks
NavigateMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Improving Text-guided Object Inpainting with Semantic Pre-inpainting
Recent years have witnessed the success of large text-to-image diffusion models and their remarkable potential to generate high-quality images. The further pursuit of enhancing the editability of images has sparked signi…
DenoisingObjectMTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting
Advancements in generative models have enabled image inpainting models to generate content within specific regions of an image based on provided prompts and masks. However, existing inpainting methods often suffer from p…
Image Inpainting3D-Consistent Image Inpainting with Diffusion Models
We address the problem of 3D inconsistency of image inpainting based on diffusion models. We propose a generative model using image pairs that belong to the same scene. To achieve the 3D-consistent and semantically coher…
DenoisingImage InpaintingInductive BiasGuidPaint: Class-Guided Image Inpainting with Diffusion Models
In recent years, diffusion models have been widely adopted for image inpainting tasks due to their powerful generative capabilities, achieving impressive results. Existing multimodal inpainting methods based on diffusion…
Image InpaintingInverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting
Recent diffusion-based models achieve photorealism in image inpainting but require many sampling steps, limiting practical use. Few-step text-to-image models offer faster generation, but naively applying them to inpainti…
Image Inpainting