# Point Map Estimation on THuman 2.1 (In-domain)

Source: [Point Map Estimation on THuman 2.1 (In-domain)](<https://www.sota2.com/research/sota/point-map-estimation-on-thuman-2-1-in-domain>)

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

Data updated: 2026-04-14T07:58:09.924Z

Evaluation of Point Map Estimation performance on the in-domain split of the THuman 2.1 dataset, reporting Accuracy (Acc), Completeness (Comp), and Normal Consistency (NC).

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 | Point Map Estimation |
| Dataset (including any stated split) | THuman 2.1 (In-domain) |
| Metric | Accuracy (Acc) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Accuracy (Acc)](<https://www.sota2.com/research/sota/point-map-estimation-on-thuman-2-1-in-domain.md?metric=Accuracy%20(Acc)>): Higher is better; unit: SCALAR.

- [Completeness (Comp)](<https://www.sota2.com/research/sota/point-map-estimation-on-thuman-2-1-in-domain.md?metric=Completeness%20(Comp)>): Lower is better; unit: SCALAR.

- [Normal Consistency (NC)](<https://www.sota2.com/research/sota/point-map-estimation-on-thuman-2-1-in-domain.md?metric=Normal%20Consistency%20(NC)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Acc) | Result date | Report paper |
| --- | --- | --- | --- |
| PiSSA | 4.292 | Not recorded | 69ddc9f17d0172140ec7989f |
| PiSSA | 4.052 | Not recorded | 69ddc9f17d0172140ec7989f |
| PiSSA | 3.931 | Not recorded | 69ddc9f17d0172140ec7989f |
| LoRA | 3.521 | Not recorded | 69ddc9f17d0172140ec7989f |
| Ours | 3.392 | Not recorded | 69ddc9f17d0172140ec7989f |
| Ours | 3.332 | Not recorded | 69ddc9f17d0172140ec7989f |
| PiSSA | 3.228 | Not recorded | 69ddc9f17d0172140ec7989f |
| LoRA | 3.195 | Not recorded | 69ddc9f17d0172140ec7989f |
| LoRA | 3.188 | Not recorded | 69ddc9f17d0172140ec7989f |
| Full | 3.053 | Not recorded | 69ddc9f17d0172140ec7989f |
| PiSSA | 3.009 | Not recorded | 69ddc9f17d0172140ec7989f |
| LoRA | 2.849 | Not recorded | 69ddc9f17d0172140ec7989f |
| VGGT | 2.816 | Not recorded | 69ddc9f17d0172140ec7989f |
| LoRA | 2.791 | Not recorded | 69ddc9f17d0172140ec7989f |
| Ours | 2.745 | Not recorded | 69ddc9f17d0172140ec7989f |

### PiSSA

Accuracy (Acc): 4.292. Result ID: 69ddf39047f34ce924c52d7c.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea75a24.md>)

[Implementation](<https://github.com/GraphPKU/PiSSA>)

Recorded evaluation configuration: {"rank":"256","# Trainable Param.":"261.4 M"}. This record does not assert independent reproduction.

### PiSSA

Accuracy (Acc): 4.052. Result ID: 69ddf39047f34ce924c52d7b.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea75a24.md>)

[Implementation](<https://github.com/GraphPKU/PiSSA>)

Recorded evaluation configuration: {"rank":"128","# Trainable Param.":"130.7 M"}. This record does not assert independent reproduction.

### PiSSA

Accuracy (Acc): 3.931. Result ID: 69ddf39047f34ce924c52d7a.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea75a24.md>)

[Implementation](<https://github.com/GraphPKU/PiSSA>)

Recorded evaluation configuration: {"rank":"64","# Trainable Param.":"65.3 M"}. This record does not assert independent reproduction.

### LoRA

Accuracy (Acc): 3.521. Result ID: 69ddf39047f34ce924c52d77.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"rank":"256","# Trainable Param.":"261.4 M"}. This record does not assert independent reproduction.

### Ours

Accuracy (Acc): 3.392. Result ID: 69ddf39047f34ce924c52d7d.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

Recorded evaluation configuration: {"d":"16","# Trainable Param.":"4.7 M"}. This record does not assert independent reproduction.

### Ours

Accuracy (Acc): 3.332. Result ID: 69ddf39047f34ce924c52d7e.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

Recorded evaluation configuration: {"d":"32","# Trainable Param.":"7.6 M"}. This record does not assert independent reproduction.

### PiSSA

Accuracy (Acc): 3.228. Result ID: 69ddf39047f34ce924c52d79.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea75a24.md>)

[Implementation](<https://github.com/GraphPKU/PiSSA>)

Recorded evaluation configuration: {"rank":"32","# Trainable Param.":"32.7 M"}. This record does not assert independent reproduction.

### LoRA

Accuracy (Acc): 3.195. Result ID: 69ddf39047f34ce924c52d73.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"rank":"16","# Trainable Param.":"16.3 M"}. This record does not assert independent reproduction.

### LoRA

Accuracy (Acc): 3.188. Result ID: 69ddf39047f34ce924c52d76.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"rank":"128","# Trainable Param.":"130.7 M"}. This record does not assert independent reproduction.

### Full

Accuracy (Acc): 3.053. Result ID: 69ddf39047f34ce924c52d72.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

Recorded evaluation configuration: {"# Trainable Param.":"853.6 M"}. This record does not assert independent reproduction.

### PiSSA

Accuracy (Acc): 3.009. Result ID: 69ddf39047f34ce924c52d78.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77dc1e209131cea75a24.md>)

[Implementation](<https://github.com/GraphPKU/PiSSA>)

Recorded evaluation configuration: {"rank":"16","# Trainable Param.":"16.3 M"}. This record does not assert independent reproduction.

### LoRA

Accuracy (Acc): 2.849. Result ID: 69ddf39047f34ce924c52d74.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"rank":"32","# Trainable Param.":"32.7 M"}. This record does not assert independent reproduction.

### VGGT

Accuracy (Acc): 2.816. Result ID: 69ddf39047f34ce924c52d71.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea736f0.md>)

[Implementation](<https://github.com/facebookresearch/vggt>)

Recorded evaluation configuration: {"# Trainable Param.":"-"}. This record does not assert independent reproduction.

### LoRA

Accuracy (Acc): 2.791. Result ID: 69ddf39047f34ce924c52d75.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"rank":"64","# Trainable Param.":"65.3 M"}. This record does not assert independent reproduction.

### Ours

Accuracy (Acc): 2.745. Result ID: 69ddf39047f34ce924c52d7f.

[Reporting paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddc9f17d0172140ec7989f.md>)

Recorded evaluation configuration: {"d":"64","# Trainable Param.":"19.3 M"}. This record does not assert independent reproduction.

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