Research map / 3D vision / 3D generation
VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturing
Shang Liu, Chaohui Yu, Chenjie Cao, Wen Qian, Fan Wang
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 distance score to the multi-view aggregation (ablation) | VCD-Texture MV-AR · SubTex | ClipFID: 7.39 -> 7.25 | Improved |
| add joint noise prediction (3D-2D self-attention) (ablation) | VCD-Texture · SubTex | ClipVar: 83.12 -> 83.62 | Improved |
| add variance alignment after rasterization (ablation) | VCD-Texture · SubTex | FID: 58.02 -> 56.05 | Improved |
| add inpainting refinement (ablation) | VCD-Texture · SubTex | FID: 56.05 -> 56.29 | No clear effect |
| increase the number of views from 4 to 9 (ablation) | VCD-Texture · SubTex | FID: 51.47 -> 59.71 | Hurt |
| increase the number of views from 4 to 9 (ablation) | VCD-Texture · SubTex | ClipVar: 82.13 -> 84.03 | Improved |
| sample 4 pixel-aggregation views instead of 9 while denoising with 9 views (ablation) | VCD-Texture · SubTex | FID: 59.71 -> 56.05 | Improved |
| VCD-Texture vs SyncMVD on SubObj | VCD-Texture · SubObj | ClipVar: 84.52 -> 83.64 | Mixed |
| Fast variant: 30 steps, coarser mesh, no inpainting | VCD-Texture · SubTex | FID: 56.29 -> 62.57 FID; 104.00 -> 74.40 s | Mixed |
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.
- Text2Tex — Text2Tex: Text-driven Texture Synthesis via Diffusion Models (ICCV 2023) · better on 2 of 2 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
- GenesisTex: Adapting Image Denoising Diffusion to Texture Space (CVPR 2024 · similarity 0.89)
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape (ICLR 2024 · similarity 0.89)
- HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance (ICLR 2024 · similarity 0.88)
- Single Mesh Diffusion Models with Field Latents for Texture Generation (CVPR 2024 · similarity 0.88)
- PaintHuman: Towards High-Fidelity Text-to-3D Human Texturing via Denoised Score Distillation (AAAI 2024 · similarity 0.87)
- Text-Guided 3D Face Synthesis - From Generation to Editing (CVPR 2024 · similarity 0.87)
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.
