← Back to all news
arXiv Computer Vision By Yanshu Zhang, George Shramko, Pratul P. Srinivasan, Ke Li

PointGT: Simultaneous Geometry and Texture Editing for Point-Based Representations

Read the original on arXiv Computer Vision →

PointGT is a point-based 3D representation that allows simultaneous editing of both geometry and texture. It combines a point-based structure, which is well-suited for geometry deformations, with a learned UV mapping technique that supports high-resolution texture editing. The method demonstrates fine-grained editing capabilities while maintaining high rendering quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
Sep 3

PointGT: Simultaneous Geometry and Texture Editing for Point-Based Representations

PointGT is a point-based 3D representation that allows simultaneous editing of both object geometry and appearance. Unlike volumetric 3D representations, which are hard to edit, PointGT combines a geometry-friendly point structure with a learned UV mapping for high-resolution texture editing. The method demonstrates fine-grained edits to geometry and texture while maintaining high rendering quality.

More like this →
arXiv Computer Vision
Sep 4

P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing

P-CORE introduces a self‑supervised surface consistency technique for point‑based neural representations, enabling robust adaptation to large deformations without needing ground‑truth deformed images. By generating random deformations and enforcing that the predicted surface after deformation matches the deformation applied to the original surface prediction, the method leverages attention‑based point representations with a learned interpolation kernel. Experiments on synthetic benchmarks and real‑world datasets show improved zero‑shot editing performance and reduced artifacts compared to existing point‑based approaches.

By Yanshu Zhang, Shichong Peng, Mehran Aghabozorgi, Alireza Moazeni, Ke Li
benchmarks
More like this →