Research map / Video / Video generation
From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos
Chenjian Gao, Lihe Ding, Rui Han, Zhanpeng Huang, Zibin Wang, Tianfan Xue
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add shading-driven enhancement instead of direct sRGB enhancement (ablation) | Bracelet insertion pipeline · Bracelet insertion (qualitative) | visual realism | Improved |
| add 3DGS-based temporal smoothing instead of no smoothing or EbSynth (ablation) | Bracelet insertion pipeline · Bracelet insertion (qualitative) | temporal smoothness | Improved |
| hybrid 3DGS rendering plus diffusion enhancement versus AnyV2V | Bracelet insertion pipeline · Bracelet insertion (56 cases) | DeQA score: 3.41 -> 3.66 | Improved |
| hybrid pipeline versus ReVideo on temporal consistency | Bracelet insertion pipeline · Bracelet insertion (56 cases) | Temporal consistency: 0.977 -> 0.984 | Improved |
| hybrid pipeline versus ReVideo on CLIP score | Bracelet insertion pipeline · Bracelet insertion (56 cases) | CLIP score: 0.661 -> 0.662 | No clear effect |
| hybrid pipeline versus best baseline in user study realism | Bracelet insertion pipeline · Bracelet insertion user study (36 participants) | Realism preference: 8.7% -> 81.7% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ReVideo — ReVideo: Remake a Video with Motion and Content Control (NeurIPS 2024) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting (CVPR 2025 · similarity 0.86)
- HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting (CVPR 2025 · similarity 0.86)
- 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors (NeurIPS 2024 · similarity 0.86)
- 3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing (ICLR 2025 · similarity 0.85)
- MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation (NeurIPS 2025 · similarity 0.85)
- Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
