Research map / 3D vision / 3D generation
CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction
Jisu Shin, Richard Shaw, Seunghyun Shin, Zhensong Zhang, Hae-Gon Jeon, Eduardo Pérez-Pellitero
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 |
|---|---|---|---|
| process the whole multi-view sequence jointly instead of single frames (ablation) | CHROMA · LOM | PSNR CC: 26.19 -> 26.25 | Improved |
| use proposed reference selection instead of a random reference frame (ablation) | CHROMA · LOM | PSNR CC: 25.11 -> 26.25 | Improved |
| combine exposure/entropy score with DINO instead of DINO-only reference selection (ablation) | CHROMA · LOM | PSNR CC: 25.95 -> 26.25 | Improved |
| add self-supervised rendering loss with unpaired WildRGBD data (ablation) | CHROMA · BilaRF | PSNR CC: 25.21 -> 25.60 | Improved |
| add self-supervised loss (ablation) | CHROMA · BilaRF | SSIM CC: 0.8245 -> 0.8240 | No clear effect |
| add CHROMA harmonization to DashGS | DashGS · DL3DV w/ ISP variation | PSNR: 23.35 -> 26.45 | Improved |
| add CHROMA harmonization to 3DGS | 3DGS · DL3DV w/ ISP variation | PSNR: 21.43 -> 25.26 | Improved |
| add CHROMA harmonization to 3DGS | 3DGS · LOM varying exposure | PSNR CC: 21.00 -> 26.25 | Improved |
| add CHROMA harmonization to DashGS | DashGS · LOM varying exposure | PSNR: 17.01 -> 18.19 | Mixed |
| add CHROMA harmonization to 3DGS | 3DGS · DL3DV w/ ISP variation | training time: 3m 39s -> 3m 55s | Hurt |
| use feed-forward multi-view harmonization instead of per-frame 2D exposure correction (UEC) | 3DGS pipeline · LOM varying exposure | temporal flickering: 0.8124 -> 0.8428 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Luminance-GS — Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment (CVPR 2025) · better on 2 of 2 shared results
- WildGaussians — WildGaussians: 3D Gaussian Splatting In the Wild (NeurIPS 2024) · 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
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.87)
- SimVS: Simulating World Inconsistencies for Robust View Synthesis (CVPR 2025 · similarity 0.86)
- ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion (CVPR 2024 · similarity 0.86)
- WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild (NeurIPS 2025 · similarity 0.86)
- HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D (CVPR 2024 · similarity 0.86)
- MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation (CVPR 2024 · similarity 0.86)
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.
