Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2507.20331 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908470003892224 |
|---|---|
| author | Gao, Chenjian Ding, Lihe Han, Rui Huang, Zhanpeng Wang, Zibin Xue, Tianfan |
| author_facet | Gao, Chenjian Ding, Lihe Han, Rui Huang, Zhanpeng Wang, Zibin Xue, Tianfan |
| contents | Inserting 3D objects into videos is a longstanding challenge in computer graphics with applications in augmented reality, virtual try-on, and video composition. Achieving both temporal consistency, or realistic lighting remains difficult, particularly in dynamic scenarios with complex object motion, perspective changes, and varying illumination. While 2D diffusion models have shown promise for producing photorealistic edits, they often struggle with maintaining temporal coherence across frames. Conversely, traditional 3D rendering methods excel in spatial and temporal consistency but fall short in achieving photorealistic lighting. In this work, we propose a hybrid object insertion pipeline that combines the strengths of both paradigms. Specifically, we focus on inserting bracelets into dynamic wrist scenes, leveraging the high temporal consistency of 3D Gaussian Splatting (3DGS) for initial rendering and refining the results using a 2D diffusion-based enhancement model to ensure realistic lighting interactions. Our method introduces a shading-driven pipeline that separates intrinsic object properties (albedo, shading, reflectance) and refines both shading and sRGB images for photorealism. To maintain temporal coherence, we optimize the 3DGS model with multi-frame weighted adjustments. This is the first approach to synergize 3D rendering and 2D diffusion for video object insertion, offering a robust solution for realistic and consistent video editing. Project Page: https://cjeen.github.io/BraceletPaper/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20331 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos Gao, Chenjian Ding, Lihe Han, Rui Huang, Zhanpeng Wang, Zibin Xue, Tianfan Computer Vision and Pattern Recognition Inserting 3D objects into videos is a longstanding challenge in computer graphics with applications in augmented reality, virtual try-on, and video composition. Achieving both temporal consistency, or realistic lighting remains difficult, particularly in dynamic scenarios with complex object motion, perspective changes, and varying illumination. While 2D diffusion models have shown promise for producing photorealistic edits, they often struggle with maintaining temporal coherence across frames. Conversely, traditional 3D rendering methods excel in spatial and temporal consistency but fall short in achieving photorealistic lighting. In this work, we propose a hybrid object insertion pipeline that combines the strengths of both paradigms. Specifically, we focus on inserting bracelets into dynamic wrist scenes, leveraging the high temporal consistency of 3D Gaussian Splatting (3DGS) for initial rendering and refining the results using a 2D diffusion-based enhancement model to ensure realistic lighting interactions. Our method introduces a shading-driven pipeline that separates intrinsic object properties (albedo, shading, reflectance) and refines both shading and sRGB images for photorealism. To maintain temporal coherence, we optimize the 3DGS model with multi-frame weighted adjustments. This is the first approach to synergize 3D rendering and 2D diffusion for video object insertion, offering a robust solution for realistic and consistent video editing. Project Page: https://cjeen.github.io/BraceletPaper/ |
| title | From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.20331 |