paper-with-me

홈 › Papers

TAPESTRY: From Geometry to Appearance via Consistent Turntable Videos

2026-03-18 · Yan Zeng, Haoran Jiang, Kaixin Yao, Qixuan Zhang, Longwen Zhang, Lan Xu, Jingyi Yu arxiv

Automatically generating photorealistic and self-consistent appearances for untextured 3D models is a critical challenge in digital content creation. The advancement of large-scale video generation models offers a natural approach: directly synthesizing 360-degree turntable videos (TTVs), which can serve not only as high-quality dynamic previews but also as an intermediate representation to drive texture synthesis and neural rendering. However, existing general-purpose video diffusion models struggle to maintain strict geometric consistency and appearance stability across the full range of views, making their outputs ill-suited for high-quality 3D reconstruction. To this end, we introduce TAPESTRY, a framework for generating high-fidelity TTVs conditioned on explicit 3D geometry. We reframe the 3D appearance generation task as a geometry-conditioned video diffusion problem: given a 3D mesh, we first render and encode multi-modal geometric features to constrain the video generation process with pixel-level precision, thereby enabling the creation of high-quality and consistent TTVs. Building upon this, we also design a method for downstream reconstruction tasks from the TTV input, featuring a multi-stage pipeline with 3D-Aware Inpainting. By rotating the model and performing a context-aware secondary generation, this pipeline effectively completes self-occluded regions to achieve full surface coverage. The videos generated by TAPESTRY are not only high-quality dynamic previews but also serve as a reliable, 3D-aware intermediate representation that can be seamlessly back-projected into UV textures or used to supervise neural rendering methods like 3DGS. This enables the automated creation of production-ready, complete 3D assets from untextured meshes. Experimental results demonstrate that our method outperforms existing approaches in both video consistency and final reconstruction quality.

📄 PDF Abstract BibTeX arXiv:2603.17735

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionVideo Generation

Similar Papers 제목 키워드 기반

Accidental Turntables: Learning 3D Pose by Watching Objects Turn

2022-12-13 · Zezhou Cheng, Matheus Gadelha, Subhransu Maji

We propose a technique for learning single-view 3D object pose estimation models by utilizing a new source of data -- in-the-wild videos where objects turn. Such videos are prevalent in practice (e.g., cars in roundabout…

3D Pose EstimationPose Estimation

What Matters in Detecting AI-Generated Videos like Sora?

2024-06-27 · Chirui Chang, Zhengzhe Liu, Xiaoyang Lyu, Xiaojuan Qi

Recent advancements in diffusion-based video generation have showcased remarkable results, yet the gap between synthetic and real-world videos remains under-explored. In this study, we examine this gap from three fundame…

Optical Flow EstimationVideo Generation

AutoScape: Geometry-Consistent Long-Horizon Scene Generation

2025-10-23 · Jiacheng Chen, Ziyu Jiang, Mingfu Liang, Bingbing Zhuang 외 arxiv

This paper proposes AutoScape, a long-horizon driving scene generation framework. At its core is a novel RGB-D diffusion model that iteratively generates sparse, geometrically consistent keyframes, serving as reliable an…

Scene GenerationPoint Clouds

Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes

2023-10-12 · Haotong Lin, Sida Peng, Zhen Xu, Tao Xie 외

This paper aims to tackle the challenge of dynamic view synthesis from multi-view videos. The key observation is that while previous grid-based methods offer consistent rendering, they fall short in capturing appearance …

GPUNovel View Synthesis

ShapeGen4D: Towards High Quality 4D Shape Generation from Videos

2025-10-07 · Jiraphon Yenphraphai, Ashkan Mirzaei, Jianqi Chen, Jiaxu Zou 외 arxiv

Video-conditioned 4D shape generation aims to recover time-varying 3D geometry and view-consistent appearance directly from an input video. In this work, we introduce a native video-to-4D shape generation framework that …