paper-with-me

Papers

ProxyImg: Towards Highly-Controllable Image Representation via Hierarchical Disentangled Proxy Embedding

2026-02-02 · Ye Chen, Yupeng Zhu, Xiongzhen Zhang, Zhewen Wan, Yingzhe Li, Wenjun Zhang, Bingbing Ni arxiv

Prevailing image representation methods, including explicit representations such as raster images and Gaussian primitives, as well as implicit representations such as latent images, either suffer from representation redundancy that leads to heavy manual editing effort, or lack a direct mapping from latent variables to semantic instances or parts, making fine-grained manipulation difficult. These limitations hinder efficient and controllable image and video editing. To address these issues, we propose a hierarchical proxy-based parametric image representation that disentangles semantic, geometric, and textural attributes into independent and manipulable parameter spaces. Based on a semantic-aware decomposition of the input image, our representation constructs hierarchical proxy geometries through adaptive Bezier fitting and iterative internal region subdivision and meshing. Multi-scale implicit texture parameters are embedded into the resulting geometry-aware distributed proxy nodes, enabling continuous high-fidelity reconstruction in the pixel domain and instance- or part-independent semantic editing. In addition, we introduce a locality-adaptive feature indexing mechanism to ensure spatial texture coherence, which further supports high-quality background completion without relying on generative models. Extensive experiments on image reconstruction and editing benchmarks, including ImageNet, OIR-Bench, and HumanEdit, demonstrate that our method achieves state-of-the-art rendering fidelity with significantly fewer parameters, while enabling intuitive, interactive, and physically plausible manipulation. Moreover, by integrating proxy nodes with Position-Based Dynamics, our framework supports real-time physics-driven animation using lightweight implicit rendering, achieving superior temporal consistency and visual realism compared with generative approaches.

📄 PDF Abstract BibTeX arXiv:2602.01881

Code (0)

등록된 구현이 없습니다.

Tasks

Image Reconstruction

Similar Papers 제목 키워드 기반

3DProxyImg: Controllable 3D-Aware Animation Synthesis from Single Image via 2D-3D Aligned Proxy Embedding

2025-12-17 · Yupeng Zhu, Xiongzhen Zhang, Ye Chen, Bingbing Ni arxiv

3D animation is central to modern visual media, yet traditional production pipelines remain labor-intensive, expertise-demanding, and computationally expensive. Recent AIGC-based approaches partially automate asset creat…

Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaption

2024-06-02 · Anqi Li, Feng Li, Yuxi Liu, Runmin Cong 외

Although recent generative image compression methods have demonstrated impressive potential in optimizing the rate-distortion-perception trade-off, they still face the critical challenge of flexible rate adaption to dive…

AllImage Compression

Hierarchical Gaussian Mixture Model Splatting for Efficient and Part Controllable 3D Generation

2025-01-01 · CVPR 2025 1 · Qitong Yang, Mingtao Feng, Zijie Wu, Weisheng Dong 외

3D content creation has achieved significant progress in terms of both quality and speed. Although current Gaussian Splatting-based methods can produce 3D objects within seconds, they are still limited by complex pre…

3D GenerationMamba

Text2Human: Text-Driven Controllable Human Image Generation

2022-05-31 · Yuming Jiang, Shuai Yang, Haonan Qiu, Wayne Wu 외

Generating high-quality and diverse human images is an important yet challenging task in vision and graphics. However, existing generative models often fall short under the high diversity of clothing shapes and textures.…

DiversityHuman ParsingImage GenerationMixture-of-Experts

TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

2022-03-31 · CVPR 2022 1 · Yanbo Xu, Yueqin Yin, Liming Jiang, Qianyi Wu 외

Recent advances like StyleGAN have promoted the growth of controllable facial editing. To address its core challenge of attribute decoupling in a single latent space, attempts have been made to adopt dual-space GAN for b…

AttributeDisentanglementFacial Editing