# Paint Bucket Colorization on 3D rendered (test)

Source: [Paint Bucket Colorization on 3D rendered (test)](<https://www.sota2.com/research/sota/paint-bucket-colorization-on-3d-rendered-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:26:44.294Z

Evaluation of Paint Bucket Colorization performance on the test split of the 3D rendered dataset, measured using metrics such as Accuracy (Acc), Pixel Accuracy (Pix-Acc), and Mean IoU (Pix-B-MIoU).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Paint Bucket Colorization |
| Dataset (including any stated split) | 3D rendered (test) |
| Metric | Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Acc](<https://www.sota2.com/research/sota/paint-bucket-colorization-on-3d-rendered-test.md?metric=Acc>): Higher is better; unit: PERCENT.

- [Acc (Thres)](<https://www.sota2.com/research/sota/paint-bucket-colorization-on-3d-rendered-test.md?metric=Acc%20(Thres)>): Higher is better; unit: PERCENT.

- [Pix-Acc](<https://www.sota2.com/research/sota/paint-bucket-colorization-on-3d-rendered-test.md?metric=Pix-Acc>): Higher is better; unit: PERCENT.

- [Pix-F-Acc](<https://www.sota2.com/research/sota/paint-bucket-colorization-on-3d-rendered-test.md?metric=Pix-F-Acc>): Higher is better; unit: PERCENT.

- [Pix-B-MIoU](<https://www.sota2.com/research/sota/paint-bucket-colorization-on-3d-rendered-test.md?metric=Pix-B-MIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Acc | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 82.66 | Not recorded | 68fa72b71e209131cea581cd |
| RAFT (F) | 71.33 | Not recorded | 68fa72b71e209131cea581cd |
| RAFT (C) | 70.28 | Not recorded | 68fa72b71e209131cea581cd |
| AnT(Cadmium) | 66.34 | Not recorded | 68fa72b71e209131cea581cd |
| RAFT | 65.89 | Not recorded | 68fa72b71e209131cea581cd |
| AnT(AnimeRun) | 55.84 | Not recorded | 68fa72b71e209131cea581cd |
| ControlNet | 17.09 | Not recorded | 68fa72b71e209131cea581cd |

### Ours

Acc: 82.66. Result ID: 699271683a6c3148490efbc0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581cd.md>)

[Implementation](<https://ykdai.github.io/projects/InclusionMatching>)

Recorded evaluation configuration: {"Type":"Inclusion matching"}. This record does not assert independent reproduction.

### RAFT (F)

Acc: 71.33. Result ID: 699271683a6c3148490efbbe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68381e209131cea1adf3.md>)

[Implementation](<https://github.com/princeton-vl/RAFT>)

Recorded evaluation configuration: {"Type":"Optical flow","Training":"MPI-Sintel","Fine-tuned":"Colorized frames"}. This record does not assert independent reproduction.

### RAFT (C)

Acc: 70.28. Result ID: 699271683a6c3148490efbbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68381e209131cea1adf3.md>)

[Implementation](<https://github.com/princeton-vl/RAFT>)

Recorded evaluation configuration: {"Type":"Optical flow","Training":"MPI-Sintel","Fine-tuned":"Contours"}. This record does not assert independent reproduction.

### AnT(Cadmium)

Acc: 66.34. Result ID: 699271683a6c3148490efbbc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ab71e209131cea29fd0.md>)

Recorded evaluation configuration: {"Type":"Segment matching"}. This record does not assert independent reproduction.

### RAFT

Acc: 65.89. Result ID: 699271683a6c3148490efbbd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68381e209131cea1adf3.md>)

[Implementation](<https://github.com/princeton-vl/RAFT>)

Recorded evaluation configuration: {"Type":"Optical flow","Training":"MPI-Sintel"}. This record does not assert independent reproduction.

### AnT(AnimeRun)

Acc: 55.84. Result ID: 699271683a6c3148490efbbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6de61e209131cea3cca4.md>)

[Implementation](<https://github.com/lisiyao21/AnimeRun>)

Recorded evaluation configuration: {"Type":"Segment matching"}. This record does not assert independent reproduction.

### ControlNet

Acc: 17.09. Result ID: 699271683a6c3148490efbba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b71e209131cea581cd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71481e209131cea50695.md>)

Recorded evaluation configuration: {"Type":"Reference-based"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
