paper-with-me

Papers

RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation

2022-11-17 · CVPR 2023 1 · Titas Anciukevičius, Zexiang Xu, Matthew Fisher, Paul Henderson, Hakan Bilen, Niloy J. Mitra, Paul Guerrero

Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D generation or single-view object reconstruction. In this paper, we present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision. Central to our method is a novel image denoising architecture that generates and renders an intermediate three-dimensional representation of a scene in each denoising step. This enforces a strong inductive structure within the diffusion process, providing a 3D consistent representation while only requiring 2D supervision. The resulting 3D representation can be rendered from any view. We evaluate RenderDiffusion on FFHQ, AFHQ, ShapeNet and CLEVR datasets, showing competitive performance for generation of 3D scenes and inference of 3D scenes from 2D images. Additionally, our diffusion-based approach allows us to use 2D inpainting to edit 3D scenes.

📄 PDF Abstract BibTeX arXiv:2211.09869

Code (1)

anciukevicius/renderdiffusion 공식 구현

Tasks

3D Generation3D ReconstructionDenoisingImage DenoisingImage GenerationObject ReconstructionUnconditional Image Generation

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Learning Sparse Masks for Diffusion-based Image Inpainting

2021-10-06 · Tobias Alt, Pascal Peter, Joachim Weickert

Diffusion-based inpainting is a powerful tool for the reconstruction of images from sparse data. Its quality strongly depends on the choice of known data. Optimising their spatial location -- the inpainting mask -- is ch…

Image CompressionImage Inpainting

Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion

2023-12-06 · Kira Prabhu, Jane Wu, Lynn Tsai, Peter Hedman 외

This paper presents a novel approach to inpainting 3D regions of a scene, given masked multi-view images, by distilling a 2D diffusion model into a learned 3D scene representation (e.g. a NeRF). Unlike 3D generative meth…

3D InpaintingNeRFObject

End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detection

2025-09-16 · Fei Wang, Xuecheng Wu, Zheng Zhang, Danlei Huang 외 arxiv

The powerful generative capabilities of diffusion models have significantly advanced the field of image synthesis, enhancing both full image generation and inpainting-based image editing. Despite their remarkable advance…

Image GenerationImage Editing

How Do Inpainting Artifacts Propagate to Language?

2026-02-24 · Pratham Yashwante, Davit Abrahamyan, Shresth Grover, Sukruth Rao arxiv

We study how visual artifacts introduced by diffusion-based inpainting affect language generation in vision-language models. We use a two-stage diagnostic setup in which masked image regions are reconstructed and then pr…

Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRI

2025-07-25 · Niklas Bubeck, Yundi Zhang, Suprosanna Shit, Daniel Rueckert 외 arxiv

In medical imaging, generative models are increasingly relied upon for two distinct but equally critical tasks: reconstruction, where the goal is to restore medical imaging (usually inverse problems like inpainting or su…

Image InpaintingImage Generation