paper-with-me

홈 › Papers

ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points

2025-12-08 · Ryota Okumura, Kaede Shiohara, Toshihiko Yamasaki arxiv

Recent text-to-image models, such as Stable Diffusion, have achieved impressive visual quality, yet they often suffer from geometric inconsistencies that undermine the structural realism of generated scenes. One prominent issue is vanishing point inconsistency, where projections of parallel lines fail to converge correctly in 2D space. This leads to structurally implausible geometry that degrades spatial realism, especially in architectural scenes. We propose ControlVP, a user-guided framework for correcting vanishing point inconsistencies in generated images. Our approach extends a pre-trained diffusion model by incorporating structural guidance derived from building contours. We also introduce geometric constraints that explicitly encourage alignment between image edges and perspective cues. Our method enhances global geometric consistency while maintaining visual fidelity comparable to the baselines. This capability is particularly valuable for applications that require accurate spatial structure, such as image-to-3D reconstruction. The dataset and source code are available at https://github.com/RyotaOkumura/ControlVP .

📄 PDF Abstract BibTeX arXiv:2512.07504

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion Models

2025-04-11 · Josef Bengtson, David Nilsson, Fredrik Kahl

Diffusion models for single image novel view synthesis (NVS) can generate highly realistic and plausible images, but they are limited in the geometric consistency to the given relative poses. The generated images often s…

Novel View SynthesisTest-time Adaptation

ShaDDR: Interactive Example-Based Geometry and Texture Generation via 3D Shape Detailization and Differentiable Rendering

2023-06-08 · Qimin Chen, Zhiqin Chen, Hang Zhou, Hao Zhang

We present ShaDDR, an example-based deep generative neural network which produces a high-resolution textured 3D shape through geometry detailization and conditional texture generation applied to an input coarse voxel sha…

Texture Synthesis

Sequential Attention GAN for Interactive Image Editing

2018-12-20 · Yu Cheng, Zhe Gan, Yitong Li, Jingjing Liu 외

Most existing text-to-image synthesis tasks are static single-turn generation, based on pre-defined textual descriptions of images. To explore more practical and interactive real-life applications, we introduce a new tas…

Image DescriptionImage GenerationText-to-Image Generation

RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects

2025-05-16 · CVPR 2025 1 · Jaeguk Kim, Jaewoo Park, Keuntek Lee, Nam Ik Cho

Estimating the 6D pose of unseen objects from monocular RGB images remains a challenging problem, especially due to the lack of prior object-specific knowledge. To tackle this issue, we propose RefPose, an innovative app…

6D Pose EstimationObjectPose Estimation

InstructMesh: Selective Refinement of Generative 3D Models for Fabrication

2026-08-28 · Faraz Faruqi, Ahmed Katary, Demircan Tas, Theresa Hradilak 외 arxiv

Recent advances in generative AI allow users to create 3D models from text or images. However, these models prioritize visual plausibility over geometric accuracy, often generating results with flaws that compromise thei…