3D Dense Captioning on ScanRefer (val)
106.11CIDErX-Trans2Cap (C)
Evaluation Results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| X-Trans2Cap (C)Extra 2D=true2022.03 | 106.11 | — | — | — | — | — | — | — | — | — | 49.07 | 32.25 | 65.54 | — | — | — | |
| X-Trans2Cap (C)Extra 2D=false2022.03 | 97.17 | — | — | — | — | — | — | — | — | — | 45.7 | 31.23 | 64.23 | — | — | — | |
| X-Trans2CapExtra 2D=true2022.03 | 89.73 | — | — | — | — | — | — | — | — | — | 44.25 | 31 | 64.5 | — | — | — | |
| TransCapExtra 2D=true2022.03 | 88.72 | — | — | — | — | — | — | — | — | — | 44.24 | 30.95 | 64.7 | — | — | — | |
| X-Trans2CapExtra 2D=false2022.03 | 87.09 | — | — | — | — | — | — | — | — | — | 44.12 | 30.67 | 64.37 | — | — | — | |
| 3D CoCa v2additional 2D input=true, IoU threshold=0.252026.01 | 87.05 | — | — | — | — | — | — | — | — | — | 45.1 | 31.78 | — | 62.45 | — | — | |
| 3D CoCa v2additional 2D input=false, IoU threshold=0.252026.01 | 86.95 | — | — | — | — | — | — | — | — | — | 45.99 | 31.55 | — | 63.98 | — | — | |
| 3D CoCaAdditional 2D Input=true, IoU Threshold=0.252025.04 | 86.12 | — | — | — | — | — | — | — | — | — | 44.79 | 30.75 | — | 61.45 | — | — | |
| 3D CoCaadditional 2D input=true, IoU threshold=0.252026.01 | 86.12 | — | — | — | — | — | — | — | — | — | 44.79 | 30.75 | — | 61.45 | — | — | |
| 3D CoCaAdditional 2D Input=false, IoU Threshold=0.252025.04 | 85.42 | — | — | — | — | — | — | — | — | — | 45.56 | 30.95 | — | 61.98 | — | — | |
| 3D CoCaadditional 2D input=false, IoU threshold=0.252026.01 | 85.42 | — | — | — | — | — | — | — | — | — | 45.56 | 30.95 | — | 61.98 | — | — | |
| See-It-Alladditional 2D input=false, IoU threshold=0.252026.01 | 78.68 | — | — | — | — | — | — | — | — | — | 43.25 | 29.21 | — | 63.06 | — | — | |
| 3D CoCa v2additional 2D input=false, IoU threshold=0.52026.01 | 78.63 | — | — | — | — | — | — | — | — | — | 41.55 | 28.95 | — | 61.95 | — | — | |
| BiCAadditional 2D input=false, IoU threshold=0.252026.01 | 78.42 | — | — | — | — | — | — | — | — | — | 41.46 | 28.82 | — | 60.02 | — | — | |
| BiCAadditional 2D input=true, IoU threshold=0.252026.01 | 78.35 | — | — | — | — | — | — | — | — | — | 41.2 | 28.82 | — | 59.8 | — | — | |
| See-It-Alladditional 2D input=true, IoU threshold=0.252026.01 | 78.05 | — | — | — | — | — | — | — | — | — | 42.16 | 28.74 | — | 61.7 | — | — | |
| 3D CoCaAdditional 2D Input=false, IoU Threshold=0.52025.04 | 77.13 | — | — | — | — | — | — | — | — | — | 41.23 | 28.52 | — | 57.4 | — | — | |
| 3D CoCaadditional 2D input=false, IoU threshold=0.52026.01 | 77.13 | — | — | — | — | — | — | — | — | — | 41.23 | 28.52 | — | 57.4 | — | — | |
| Vote2Cap-DETR++Additional 2D Input=true, IoU Threshold=0.252025.04 | 77.03 | — | — | — | — | — | — | — | — | — | 40.99 | 28.53 | — | 59.59 | — | — | |
| Vote2Cap-DETR++additional 2D input=true, IoU threshold=0.252026.01 | 77.03 | — | — | — | — | — | — | — | — | — | 40.99 | 28.53 | — | 59.59 | — | — | |
| Vote2Cap-DETR++Additional 2D Input=false, IoU Threshold=0.252025.04 | 76.36 | — | — | — | — | — | — | — | — | — | 41.37 | 28.7 | — | 60 | — | — | |
| Vote2Cap-DETR++additional 2D input=false, IoU threshold=0.252026.01 | 76.36 | — | — | — | — | — | — | — | — | — | 41.37 | 28.7 | — | 60 | — | — | |
| TransCapExtra 2D=false2022.03 | 75.75 | — | — | — | — | — | — | — | — | — | 42.06 | 28.82 | 62.62 | — | — | — | |
| 3D CoCa v2additional 2D input=true, IoU threshold=0.52026.01 | 75.6 | — | — | — | — | — | — | — | — | — | 38.7 | 28.25 | — | 55.63 | — | — | |
| 3D CoCaAdditional 2D Input=true, IoU Threshold=0.52025.04 | 74.52 | — | — | — | — | — | — | — | — | — | 38.42 | 28.03 | — | 55.23 | — | — | |
| 3D CoCaadditional 2D input=true, IoU threshold=0.52026.01 | 74.52 | — | — | — | — | — | — | — | — | — | 38.42 | 28.03 | — | 55.23 | — | — | |
| See-It-Alladditional 2D input=false, IoU threshold=0.52026.01 | 73.22 | — | — | — | — | — | — | — | — | — | 40.91 | 28.19 | — | 60.46 | — | — | |
| Vote2Cap-DETRAdditional 2D Input=true, IoU Threshold=0.252025.04 | 72.79 | — | — | — | — | — | — | — | — | — | 39.17 | 28.06 | — | 59.23 | — | — | |
| Vote2Cap-DETRadditional 2D input=true, IoU threshold=0.252026.01 | 72.79 | — | — | — | — | — | — | — | — | — | 39.17 | 28.06 | — | 59.23 | — | — | |
| Vote2Cap-DETRAdditional 2D Input=false, IoU Threshold=0.252025.04 | 71.45 | — | — | — | — | — | — | — | — | — | 39.34 | 28.25 | — | 59.33 | — | — | |
| Vote2Cap-DETRadditional 2D input=false, IoU threshold=0.252026.01 | 71.45 | — | — | — | — | — | — | — | — | — | 39.34 | 28.25 | — | 59.33 | — | — | |
| 3D-VLPAdditional 2D Input=true, IoU Threshold=0.252025.04 | 70.73 | — | — | — | — | — | — | — | — | — | 41.03 | 28.14 | — | 59.72 | — | — | |
| 3D-VLPadditional 2D input=true, IoU threshold=0.252026.01 | 70.73 | — | — | — | — | — | — | — | — | — | 41.03 | 28.14 | — | 59.72 | — | — | |
| Scan2Cap (Inst)Extra 2D=true2022.03 | 70.04 | — | — | — | — | — | — | — | — | — | 41.57 | 29.67 | 64.1 | — | — | — | |
| See-It-Alladditional 2D input=true, IoU threshold=0.52026.01 | 69.86 | — | — | — | — | — | — | — | — | — | 37.89 | 27.04 | — | 57.33 | — | — | |
| BiCAadditional 2D input=false, IoU threshold=0.52026.01 | 68.46 | — | — | — | — | — | — | — | — | — | 38.23 | 27.56 | — | 58.56 | — | — | |
| Scan2CapExtra 2D=true2022.03 | 67.95 | — | — | — | — | — | — | — | — | — | 41.49 | 29.23 | 63.66 | — | — | — | |
| Vote2Cap-DETR++Additional 2D Input=false, IoU Threshold=0.52025.04 | 67.58 | — | — | — | — | — | — | — | — | — | 37.05 | 26.89 | — | 55.64 | — | — | |
| Vote2Cap-DETR++additional 2D input=false, IoU threshold=0.52026.01 | 67.58 | — | — | — | — | — | — | — | — | — | 37.05 | 26.89 | — | 55.64 | — | — | |
| BiCAadditional 2D input=true, IoU threshold=0.52026.01 | 66.47 | — | — | — | — | — | — | — | — | — | 36.13 | 26.71 | — | 54.54 | — | — | |
| Unit3DAdditional 2D Input=true, IoU Threshold=0.252025.04 | 66.19 | — | — | — | — | — | — | — | — | — | 29.22 | 21.31 | — | 45.98 | — | — | |
| Scan2CapExtra 2D=false2022.03 | 65.79 | — | — | — | — | — | — | — | — | — | 38.54 | 28.81 | 61.93 | — | — | — | |
| 3DJCGAdditional 2D Input=true, IoU Threshold=0.252025.04 | 64.7 | — | — | — | — | — | — | — | — | — | 40.17 | 27.66 | — | 59.23 | — | — | |
| 3DJCGadditional 2D input=true, IoU threshold=0.252026.01 | 64.7 | — | — | — | — | — | — | — | — | — | 40.17 | 27.66 | — | 59.23 | — | — | |
| Scan2Cap (Inst)Extra 2D=false2022.03 | 64.44 | — | — | — | — | — | — | — | — | — | 36.89 | 28.42 | 60.42 | — | — | — | |
| Vote2Cap-DETR++Additional 2D Input=true, IoU Threshold=0.52025.04 | 64.32 | — | — | — | — | — | — | — | — | — | 34.73 | 26.04 | — | 53.67 | — | — | |
| Vote2Cap-DETR++additional 2D input=true, IoU threshold=0.52026.01 | 64.32 | — | — | — | — | — | — | — | — | — | 34.73 | 26.04 | — | 53.67 | — | — | |
| 3D-VLPAdditional 2D Input=false, IoU Threshold=0.252025.04 | 64.09 | — | — | — | — | — | — | — | — | — | 39.84 | 27.65 | — | 58.78 | — | — | |
| 3D-VLPadditional 2D input=false, IoU threshold=0.252026.01 | 64.09 | — | — | — | — | — | — | — | — | — | 39.84 | 27.65 | — | 58.78 | — | — | |
| SpaCap3dAdditional 2D Input=true, IoU Threshold=0.252025.04 | 63.3 | — | — | — | — | — | — | — | — | — | 36.46 | 26.71 | — | 55.71 | — | — | |
| SpaCap3dadditional 2D input=true, IoU threshold=0.252026.01 | 63.3 | — | — | — | — | — | — | — | — | — | 36.46 | 26.71 | — | 55.71 | — | — | |
| MOREAdditional 2D Input=true, IoU Threshold=0.252025.04 | 62.91 | — | — | — | — | — | — | — | — | — | 36.25 | 26.75 | — | 56.33 | — | — | |
| MOREadditional 2D input=true, IoU threshold=0.252026.01 | 62.91 | — | — | — | — | — | — | — | — | — | 36.25 | 26.75 | — | 56.33 | — | — | |
| Vote2Cap-DETRAdditional 2D Input=false, IoU Threshold=0.52025.04 | 61.81 | — | — | — | — | — | — | — | — | — | 34.46 | 26.22 | — | 54.4 | — | — | |
| Vote2Cap-DETRadditional 2D input=false, IoU threshold=0.52026.01 | 61.81 | — | — | — | — | — | — | — | — | — | 34.46 | 26.22 | — | 54.4 | — | — | |
| 3DJCGAdditional 2D Input=false, IoU Threshold=0.252025.04 | 60.86 | — | — | — | — | — | — | — | — | — | 39.67 | 27.45 | — | 59.02 | — | — | |
| 3DJCGadditional 2D input=false, IoU threshold=0.252026.01 | 60.86 | — | — | — | — | — | — | — | — | — | 39.67 | 27.45 | — | 59.02 | — | — | |
| Vote2Cap-DETRAdditional 2D Input=true, IoU Threshold=0.52025.04 | 59.32 | — | — | — | — | — | — | — | — | — | 32.42 | 25.28 | — | 52.53 | — | — | |
| Vote2Cap-DETRadditional 2D input=true, IoU threshold=0.52026.01 | 59.32 | — | — | — | — | — | — | — | — | — | 32.42 | 25.28 | — | 52.53 | — | — | |
| MOREAdditional 2D Input=false, IoU Threshold=0.252025.04 | 58.89 | — | — | — | — | — | — | — | — | — | 35.41 | 26.36 | — | 55.41 | — | — | |
| MOREadditional 2D input=false, IoU threshold=0.252026.01 | 58.89 | — | — | — | — | — | — | — | — | — | 35.41 | 26.36 | — | 55.41 | — | — | |
| SpaCap3dAdditional 2D Input=false, IoU Threshold=0.252025.04 | 58.06 | — | — | — | — | — | — | — | — | — | 35.3 | 26.16 | — | 55.03 | — | — | |
| SpaCap3dadditional 2D input=false, IoU threshold=0.252026.01 | 58.06 | — | — | — | — | — | — | — | — | — | 35.3 | 26.16 | — | 55.03 | — | — | |
| Scan2CapAdditional 2D Input=true, IoU Threshold=0.252025.04 | 56.82 | — | — | — | — | — | — | — | — | — | 34.18 | 26.29 | — | 55.27 | — | — | |
| Scan2Capadditional 2D input=true, IoU threshold=0.252026.01 | 56.82 | — | — | — | — | — | — | — | — | — | 34.18 | 26.29 | — | 55.27 | — | — | |
| 3D-VLPAdditional 2D Input=true, IoU Threshold=0.52025.04 | 54.94 | — | — | — | — | — | — | — | — | — | 32.31 | 24.83 | — | 51.51 | — | — | |
| 3D-VLPadditional 2D input=true, IoU threshold=0.52026.01 | 54.94 | — | — | — | — | — | — | — | — | — | 32.31 | 24.83 | — | 51.51 | — | — | |
| Scan2CapAdditional 2D Input=false, IoU Threshold=0.252025.04 | 53.73 | — | — | — | — | — | — | — | — | — | 34.25 | 26.14 | — | 54.95 | — | — | |
| Scan2Capadditional 2D input=false, IoU threshold=0.252026.01 | 53.73 | — | — | — | — | — | — | — | — | — | 34.25 | 26.14 | — | 54.95 | — | — | |
| 3D-VLPAdditional 2D Input=false, IoU Threshold=0.52025.04 | 50.02 | — | — | — | — | — | — | — | — | — | 31.87 | 24.53 | — | 51.17 | — | — | |
| 3D-VLPadditional 2D input=false, IoU threshold=0.52026.01 | 50.02 | — | — | — | — | — | — | — | — | — | 31.87 | 24.53 | — | 51.17 | — | — | |
| 3DJCGAdditional 2D Input=true, IoU Threshold=0.52025.04 | 49.48 | — | — | — | — | — | — | — | — | — | 31.03 | 24.22 | — | 50.8 | — | — | |
| 3DJCGadditional 2D input=true, IoU threshold=0.52026.01 | 49.48 | — | — | — | — | — | — | — | — | — | 31.03 | 24.22 | — | 50.8 | — | — | |
| 3DJCGAdditional 2D Input=false, IoU Threshold=0.52025.04 | 47.68 | — | — | — | — | — | — | — | — | — | 31.53 | 24.28 | — | 51.8 | — | — | |
| 3DJCGadditional 2D input=false, IoU threshold=0.52026.01 | 47.68 | — | — | — | — | — | — | — | — | — | 31.53 | 24.28 | — | 51.8 | — | — | |
| Unit3DAdditional 2D Input=true, IoU Threshold=0.52025.04 | 46.69 | — | — | — | — | — | — | — | — | — | 27.22 | 21.91 | — | 45.98 | — | — | |
| Unit3Dadditional 2D input=true, IoU threshold=0.52026.01 | 46.69 | — | — | — | — | — | — | — | — | — | 27.22 | 21.91 | — | 45.98 | — | — | |
| D3NetAdditional 2D Input=true, IoU Threshold=0.52025.04 | 46.07 | — | — | — | — | — | — | — | — | — | 30.29 | 24.35 | — | 51.67 | — | — | |
| D3Netadditional 2D input=true, IoU threshold=0.52026.01 | 46.07 | — | — | — | — | — | — | — | — | — | 30.29 | 24.35 | — | 51.67 | — | — | |
| SpaCap3dAdditional 2D Input=true, IoU Threshold=0.52025.04 | 44.02 | — | — | — | — | — | — | — | — | — | 25.26 | 22.33 | — | 45.36 | — | — | |
| SpaCap3dadditional 2D input=true, IoU threshold=0.52026.01 | 44.02 | — | — | — | — | — | — | — | — | — | 25.26 | 22.33 | — | 45.36 | — | — | |
| SpaCap3dAdditional 2D Input=false, IoU Threshold=0.52025.04 | 42.76 | — | — | — | — | — | — | — | — | — | 25.38 | 22.84 | — | 45.66 | — | — | |
| SpaCap3dadditional 2D input=false, IoU threshold=0.52026.01 | 42.76 | — | — | — | — | — | — | — | — | — | 25.38 | 22.84 | — | 45.66 | — | — | |
| MOREAdditional 2D Input=true, IoU Threshold=0.52025.04 | 40.94 | — | — | — | — | — | — | — | — | — | 22.93 | 21.66 | — | 44.42 | — | — | |
| MOREadditional 2D input=true, IoU threshold=0.52026.01 | 40.94 | — | — | — | — | — | — | — | — | — | 22.93 | 21.66 | — | 44.42 | — | — | |
| Scan2CapAdditional 2D Input=true, IoU Threshold=0.52025.04 | 39.08 | — | — | — | — | — | — | — | — | — | 23.32 | 21.97 | — | 44.78 | — | — | |
| Scan2Capadditional 2D input=true, IoU threshold=0.52026.01 | 39.08 | — | — | — | — | — | — | — | — | — | 23.32 | 21.97 | — | 44.78 | — | — | |
| MOREAdditional 2D Input=false, IoU Threshold=0.52025.04 | 38.98 | — | — | — | — | — | — | — | — | — | 23.01 | 21.65 | — | 44.33 | — | — | |
| MOREadditional 2D input=false, IoU threshold=0.52026.01 | 38.98 | — | — | — | — | — | — | — | — | — | 23.01 | 21.65 | — | 44.33 | — | — | |
| Scan2CapAdditional 2D Input=false, IoU Threshold=0.52025.04 | 35.2 | — | — | — | — | — | — | — | — | — | 22.36 | 21.44 | — | 43.57 | — | — | |
| Scan2Capadditional 2D input=false, IoU threshold=0.52026.01 | 35.2 | — | — | — | — | — | — | — | — | — | 22.36 | 21.44 | — | 43.57 | — | — | |
| 2D-3D Proj.Capturing=2D, Detection=Mask R-CNN2020.12 | — | 18.29 | 10.27 | 16.67 | 33.63 | 8.31 | 2.31 | 12.54 | 25.93 | 10.5 | — | — | — | — | — | — | |
| 3D-2D Proj.Capturing=2D, Detection=VoteNet2020.12 | — | 19.73 | 17.86 | 19.83 | 40.68 | 11.47 | 8.56 | 15.73 | 31.65 | 31.83 | — | — | — | — | — | — | |
| 3D-VLP∗Ldes=MLE2026.05 | — | 64.09 | 39.84 | 27.65 | — | 50.02 | 31.87 | 24.53 | — | — | — | — | — | — | 58.78 | 51.17 | |
| 3DJCGLdes=MLE2026.05 | — | 60.86 | 39.67 | 27.45 | — | 47.68 | 31.53 | 24.28 | — | — | — | — | — | — | 59.02 | 51.8 | |
| CAC(O)Ldes=MLE2026.05 | — | 75.56 | 40.34 | 28.55 | — | 68.07 | 36.53 | 26.72 | — | — | — | — | — | — | 59.53 | 55.08 | |
| CAC(O)Ldes=SCST2026.05 | — | 89.51 | 43.47 | 28.76 | — | 79.09 | 38.96 | 26.85 | — | — | — | — | — | — | 59.51 | 54.95 | |
| CAC(O&H)Ldes=MLE2026.05 | — | 78.67 | 42.11 | 28.79 | — | 69.92 | 37.67 | 26.89 | — | — | — | — | — | — | 60.22 | 55.62 | |
| CAC(O&H)Ldes=SCST2026.05 | — | 90.16 | 44.07 | 28.8 | — | 80.35 | 39.95 | 26.94 | — | — | — | — | — | — | 60.29 | 55.66 | |
| ContextualLdes=MLE2026.05 | — | — | — | — | — | 42.77 | 23.6 | 22.05 | — | — | — | — | — | — | — | 45.13 |