Monocular Depth Estimation on Sintel
0.1261Abs RelTrack4World
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Track4WorldParams=1.38B2026.03 | 0.1261 | 82.91 | — | — | — | — | — | — | |
| Pi3Params=1.29B2026.03 | 0.1489 | 78.99 | — | — | — | — | — | — | |
| DA3Params=1.36B2026.03 | 0.1575 | 80.64 | — | — | — | — | — | — | |
| ICDepthAlignment=per-frame scale-shift2026.07 | 0.186 | — | — | — | — | 78.7 | — | 4.227 | |
| DepthCrafterAlignment=per-frame scale-shift2026.07 | 0.194 | — | — | — | — | 78.4 | — | 4.694 | |
| VGGTParams=1.26B2026.03 | 0.2004 | 73.03 | — | — | — | — | — | — | |
| MoGe-2Params=331M2026.03 | 0.2058 | 69.03 | — | — | — | — | — | — | |
| MapAnythingParams=563M2026.03 | 0.2059 | 71.41 | — | — | — | — | — | — | |
| Video Depth AnythingAlignment=per-frame scale-shift2026.07 | 0.209 | — | — | — | — | 75.4 | — | 4.857 | |
| DepthAnythingV2Size(Spec)=Giant, Latency (ms)=164.25, Throughput (samples/s)=6.35, Zero-shot evaluation protocol=true2026.05 | 0.21 | 73.7 | — | — | — | — | — | — | |
| JetViT-DepthAnythingSize(Spec)=Giant(2 FA), Latency (ms)=90.65, Throughput (samples/s)=11.39, Zero-shot evaluation protocol=true2026.05 | 0.21 | 74.1 | — | — | — | — | — | — | |
| VDA-BaseParams=114.4M, FPS=42.4, Resolution=shorter side 518px, Inference protocol=independent per-frame inference2026.03 | 0.212 | 75.8 | — | — | — | — | — | 4.922 | |
| MoGeParams=314M2026.03 | 0.2181 | 66.15 | — | — | — | — | — | — | |
| DAv2-ViTBParams=97.5M, FPS=60.1, Resolution=shorter side 518px, Inference protocol=independent per-frame inference2026.03 | 0.222 | 73.3 | — | — | — | — | — | 4.867 | |
| DepthAnythingV2Size(Spec)=Large, Latency (ms)=60.76, Throughput (samples/s)=14.20, Zero-shot evaluation protocol=true2026.05 | 0.222 | 73 | — | — | — | — | — | — | |
| DAv2-ViTLParams=335.3M, FPS=21.1, Resolution=shorter side 518px, Inference protocol=independent per-frame inference2026.03 | 0.224 | 73.5 | — | — | — | — | — | 4.985 | |
| JetViT-DepthAnythingSize(Spec)=Large(2 FA), Latency (ms)=32.63, Throughput (samples/s)=32.13, Zero-shot evaluation protocol=true2026.05 | 0.226 | 73 | — | — | — | — | — | — | |
| Depth Anything V2Alignment=per-frame scale-shift2026.07 | 0.226 | — | — | — | — | 74 | — | 5.121 | |
| JetViT-DepthAnythingSize(Spec)=Large(1 FA), Latency (ms)=31.04, Throughput (samples/s)=33.72, Zero-shot evaluation protocol=true2026.05 | 0.227 | 72.6 | — | — | — | — | — | — | |
| JetViT-DepthAnythingSize(Spec)=Large(0 FA), Latency (ms)=29.70, Throughput (samples/s)=34.97, Zero-shot evaluation protocol=true2026.05 | 0.229 | 72.2 | — | — | — | — | — | — | |
| VDA-SmallParams=29.0M, FPS=75.9, Resolution=shorter side 518px, Inference protocol=independent per-frame inference2026.03 | 0.233 | 71.6 | — | — | — | — | — | 5.04 | |
| DAv2-ViTSParams=24.8M, FPS=132.1, Resolution=shorter side 518px, Inference protocol=independent per-frame inference2026.03 | 0.235 | 71.7 | — | — | — | — | — | 4.993 | |
| ViGeoAlignment=affine-invariant, Temporal Context=None2026.05 | 0.24 | — | — | — | — | 72 | — | — | |
| StreamVGGTType=Streaming2025.07 | 0.254 | 68.5 | — | — | — | — | — | — | |
| VGGTAlignment=affine-invariant2026.05 | 0.254 | — | — | — | — | 70.7 | — | — | |
| ZipMap2026.03 | 0.268 | 66.6 | — | — | — | — | — | — | |
| Pi3Alignment=affine-invariant2026.05 | 0.272 | — | — | — | — | 72.4 | — | — | |
| MoGe12026.02 | 0.273 | 69.5 | — | — | — | — | — | — | |
| MoGe v12026.03 | 0.273 | 69.5 | — | — | — | — | — | — | |
| MoGe2025.07 | 0.273 | 69.5 | — | — | — | — | — | — | |
| MoGe2025.07 | 0.273 | 69.5 | — | — | — | — | — | — | |
| MoGeMethod version=v12025.07 | 0.273 | 69.5 | — | — | — | — | — | — | |
| G2TAM2026.07 | 0.275 | 61.6 | — | — | — | — | — | — | |
| pi^32026.03 | 0.276 | 62.2 | — | — | — | — | — | — | |
| VGGTType=Dense-view2025.07 | 0.276 | 67.5 | — | — | — | — | — | — | |
| MoGe22026.02 | 0.277 | 68.7 | — | — | — | — | — | — | |
| π32026.02 | 0.277 | 61.4 | — | — | — | — | — | — | |
| MoGe v22026.03 | 0.277 | 68.7 | — | — | — | — | — | — | |
| π32025.07 | 0.277 | 61.4 | — | — | — | — | — | — | |
| MoGeMethod version=v22025.07 | 0.277 | 68.7 | — | — | — | — | — | — | |
| pi^32025.07 | 0.277 | 61.4 | — | — | — | — | — | — | |
| Pi32026.07 | 0.277 | 61.4 | — | — | — | — | — | — | |
| DA3Alignment=affine-invariant2026.05 | 0.281 | — | — | — | — | 67.3 | — | — | |
| UNITScale=Scale-Invariant2026.05 | 0.282 | 64.2 | — | — | — | — | — | 4.732 | |
| AsyncMDEParams=3.83M, FPS=237, Resolution=shorter side 518px, Inference protocol=lag 0-9 cycle averages2026.03 | 0.287 | 64 | — | — | — | — | — | 5.377 | |
| Depth Any VideoAlignment=per-frame scale-shift2026.07 | 0.287 | — | — | — | — | 72.3 | — | 5.109 | |
| FlashDepthAlignment=affine-invariant2026.05 | 0.288 | — | — | — | — | 66.4 | — | — | |
| DepthCrafterAlignment=affine-invariant2026.05 | 0.291 | — | — | — | — | 61.9 | — | — | |
| StreamVGGTScale=Scale-Invariant2026.05 | 0.294 | 63.7 | — | — | — | — | — | 5.315 | |
| TrajVG2026.02 | 0.297 | 61.7 | — | — | — | — | — | — | |
| DepthAnything3Scale=Scale-Invariant2026.05 | 0.308 | 61.6 | — | — | — | — | — | 5.143 | |
| IVGTdecoding=direct2026.05 | 0.309 | 62 | — | — | — | — | — | — | |
| VGGTScale=Scale-Invariant2026.05 | 0.32 | 62 | — | — | — | — | — | 5.81 | |
| VGGT2026.03 | 0.329 | 60 | — | — | — | — | — | — | |
| Omnizero-shot=true2026.04 | 0.334 | — | — | — | — | 74.27 | — | — | |
| VGGT2026.02 | 0.335 | 59.9 | — | — | — | — | — | — | |
| VGGT2025.07 | 0.335 | 59.9 | — | — | — | — | — | — | |
| Interp3Rskip=32026.03 | 0.335 | 57.5 | — | — | — | — | — | — | |
| VGGT2026.07 | 0.335 | 59.9 | — | — | — | — | — | — | |
| Interp3Rskip=12026.03 | 0.338 | 59.1 | — | — | — | — | — | — | |
| MASt3RType=Pair-wise2025.07 | 0.34 | 60.4 | — | — | — | — | — | — | |
| MiDaS V3 DPTSize(Spec)=Large(Swin), Latency (ms)=39.28, Throughput (samples/s)=27.14, Zero-shot evaluation protocol=true2026.05 | 0.342 | 59.8 | — | — | — | — | — | — | |
| MonST3RType=Pair-wise2025.07 | 0.358 | 54.8 | — | — | — | — | — | — | |
| VDM-EVFIskip=12026.03 | 0.366 | 54.2 | — | — | — | — | — | — | |
| π³Scale=Scale-Invariant2026.05 | 0.369 | 64.9 | — | — | — | — | — | 4.917 | |
| Metric3D v2evaluation_mode=Zero-shot2026.01 | 0.37 | — | 0.216 | 62.92 | 76.87 | — | — | — | |
| Interp3Rskip=72026.03 | 0.37 | 53.4 | — | — | — | — | — | — | |
| DA V22025.07 | 0.372 | 54.1 | — | — | — | — | — | — | |
| DA V2Evaluation variant=metric indoor2025.07 | 0.372 | 54.1 | — | — | — | — | — | — | |
| TimeLensskip=12026.03 | 0.377 | 54.8 | — | — | — | — | — | — | |
| RIFEskip=12026.03 | 0.381 | 53.8 | — | — | — | — | — | — | |
| DA3 giantzero-shot=true2026.04 | 0.3821 | — | — | — | — | 66.54 | — | — | |
| LiteMono (fine-tuned)Params=3.07M, FPS=238, Resolution=640x192, Fine-tuned=true, Inference protocol=independent per-frame inference2026.03 | 0.383 | 50.2 | — | — | — | — | — | 5.664 | |
| VDM-EVFIskip=32026.03 | 0.39 | 55.3 | — | — | — | — | — | — | |
| Point3RType=Streaming2025.07 | 0.395 | 56.8 | — | — | — | — | — | — | |
| MapAnythingScale=Scale-Invariant2026.05 | 0.395 | 59.6 | — | — | — | — | — | 5.356 | |
| VDM-EVFIskip=72026.03 | 0.397 | 55.9 | — | — | — | — | — | — | |
| IVGTdecoding=from render2026.05 | 0.398 | 57 | — | — | — | — | — | — | |
| MonST3R2026.02 | 0.402 | 52.5 | — | — | — | — | — | — | |
| MonST3R2026.03 | 0.402 | 52.5 | — | — | — | — | — | — | |
| MonST3R2025.07 | 0.402 | 52.5 | — | — | — | — | — | — | |
| MonST3R2026.07 | 0.402 | 52.5 | — | — | — | — | — | — | |
| MASt3R2026.02 | 0.413 | 56.9 | — | — | — | — | — | — | |
| MASt3R2026.03 | 0.413 | 56.9 | — | — | — | — | — | — | |
| MASt3R2025.07 | 0.413 | 56.9 | — | — | — | — | — | — | |
| MASt3R2026.07 | 0.413 | 56.9 | — | — | — | — | — | — | |
| LiteMonoParams=3.07M, FPS=238, Resolution=640x192, Inference protocol=independent per-frame inference2026.03 | 0.416 | 44.3 | — | — | — | — | — | 5.956 | |
| CUT3R2026.02 | 0.418 | 52 | — | — | — | — | — | — | |
| CUT3R2026.03 | 0.418 | 52 | — | — | — | — | — | — | |
| CUT3R2025.07 | 0.418 | 52 | — | — | — | — | — | — | |
| CUT3R2026.05 | 0.418 | 52 | — | — | — | — | — | — | |
| CUT3R2026.07 | 0.418 | 52 | — | — | — | — | — | — | |
| Interp3Rskip=152026.03 | 0.42 | 55.6 | — | — | — | — | — | — | |
| VDM-EVFIskip=152026.03 | 0.424 | 54.3 | — | — | — | — | — | — | |
| DUSt3RType=Pair-wise2025.07 | 0.424 | 58.7 | — | — | — | — | — | — | |
| CUT3RType=Streaming2025.07 | 0.428 | 55.4 | — | — | — | — | — | — | |
| ChronoDepthAlignment=per-frame scale-shift2026.07 | 0.431 | — | — | — | — | 60.3 | — | 8.565 | |
| TimeLensskip=32026.03 | 0.441 | 54.5 | — | — | — | — | — | — | |
| CUT3RParams=748.4M, FPS=14.4, Resolution=224x224, Inference protocol=independent per-frame inference2026.03 | 0.448 | 42.5 | — | — | — | — | — | 6.185 | |
| VGGTzero-shot=true2026.04 | 0.4551 | — | — | — | — | 66.11 | — | — |