paper-with-me

홈 › Papers

Neural Image Representations for Multi-Image Fusion and Layer Separation

2021-08-02 · Seonghyeon Nam, Marcus A. Brubaker, Michael S. Brown

We propose a framework for aligning and fusing multiple images into a single view using neural image representations (NIRs), also known as implicit or coordinate-based neural representations. Our framework targets burst images that exhibit camera ego motion and potential changes in the scene. We describe different strategies for alignment depending on the nature of the scene motion -- namely, perspective planar (i.e., homography), optical flow with minimal scene change, and optical flow with notable occlusion and disocclusion. With the neural image representation, our framework effectively combines multiple inputs into a single canonical view without the need for selecting one of the images as a reference frame. We demonstrate how to use this multi-frame fusion framework for various layer separation tasks. The code and results are available at https://shnnam.github.io/research/nir.

📄 PDF Abstract BibTeX arXiv:2108.01199

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing

2024-03-21 · Yueru Jia, Yuhui Yuan, Aosong Cheng, Chuke Wang 외

Recently, how to achieve precise image editing has attracted increasing attention, especially given the remarkable success of text-to-image generation models. To unify various spatial-aware image editing abilities into o…

Image Generationspatial-aware image editingText to Image GenerationText-to-Image Generation

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

2025-12-17 · Shengming Yin, Zekai Zhang, Zecheng Tang, Kaiyuan Gao 외 arxiv

Recent visual generative models often struggle with consistency during image editing due to the entangled nature of raster images, where all visual content is fused into a single canvas. In contrast, professional design …

Image GenerationImage Editing

Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers

2026-02-06 · Yuxuan Yao, Yuxuan Chen, Hui Li, Kaihui Cheng 외 arxiv

Multimodal Diffusion Transformers (MMDiTs) for text-to-image generation maintain separate text and image branches, with bidirectional information flow between text tokens and visual latents throughout denoising. In this …

Text-to-Image Generation

LayerSync: Self-aligning Intermediate Layers

2025-10-14 · Yasaman Haghighi, Bastien van Delft, Mariam Hassan, Alexandre Alahi arxiv

We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies have highlighted the connection between the quality of generation and t…

Image Generation

Collage Diffusion

2023-03-01 · Vishnu Sarukkai, Linden Li, Arden Ma, Christopher Ré 외

We seek to give users precise control over diffusion-based image generation by modeling complex scenes as sequences of layers, which define the desired spatial arrangement and visual attributes of objects in the scene. C…

Conditional Image GenerationImage GenerationImage Harmonization