List your company

3D Occupancy Prediction on Occ3D-nuScenes (val)

5,335mIoUTFusionOcc (T-SQ-IW-25600)
-173.881,256.312,686.54,116.69Jul 4, 2023Jan 1, 2024Jun 30, 2024Dec 29, 2024Jun 28, 2025Dec 26, 2025Jun 26, 2026

Evaluation results

MethodLinks
TFusionOcc (T-SQ-IW-25600)Mask=true, Backbone=Res-50, Modality=C+L, primitive_type=T-Superquadric, IW=true, tokens=256002026.025,335—————1,4666,0254,0805,8396,3673,4814,5975,9044,8724,5325,0438,3214,4705,5556,0227,1416,975———————————
TFusionOcc (T-SQ-IW-12800)Mask=true, Backbone=Res-50, Modality=C+L, primitive_type=T-Superquadric, IW=true, tokens=128002026.025,297—————1,4906,0594,0935,6486,3683,5254,5965,8374,8624,4544,9848,3424,3855,5095,9676,9866,951———————————
EFFOccMask=true, Backbone=Res-50, Modality=C+L2026.025,282—————1,2095,9673,3396,1766,4983,5464,6015,7094,1044,7875,4598,2764,3955,6376,0237,1126,960———————————
TFusionOcc (T-SQ-12800)Mask=true, Backbone=Res-50, Modality=C+L, primitive_type=T-Superquadric, tokens=128002026.025,234—————1,4825,8853,9485,5106,2243,5424,4195,8614,7174,4924,8438,2544,2875,4655,9527,1056,996———————————
TFusionOcc (T-SQ-25600)Mask=true, Backbone=Res-50, Modality=C+L, primitive_type=T-Superquadric, tokens=256002026.025,170—————1,4895,9193,7645,3966,2403,3884,4745,8414,7174,1084,7238,2464,3255,4805,9047,0346,839———————————
SDGOccMask=true, Backbone=Res-50, Modality=C+L2026.025,166—————1,3205,7802,4306,0306,4303,6203,9405,2403,5805,0905,3708,4604,7505,8006,1607,0706,770———————————
TFusionOcc (T-P-25600)Mask=true, Backbone=Res-50, Modality=C+L, primitive_type=T-Primitive, tokens=256002026.025,151—————1,4755,8103,7735,1216,2033,5554,4825,5184,3704,4334,9248,2714,2595,4835,9277,0216,941———————————
RadOccMask=true, Backbone=Swin-B, Modality=C+L2026.024,938—————1,0905,8202,5005,7906,2903,4003,3505,0103,2104,8905,2108,2904,2705,5305,8306,8606,600———————————
OccFusionMask=true, Backbone=R101-DCN, Modality=C+L2026.024,874—————1,2405,1803,3005,4605,7703,4004,3004,8403,5504,1204,8608,3004,4705,7106,0006,2506,130———————————
RM2OccMask=true, Backbone=R101-DCN, Modality=C+L2026.024,782—————1,3345,4533,3815,8305,9973,4453,4892,9433,1533,9914,2449,6014,9766,1286,7625,3715,196———————————
OccFusionMask=true, Backbone=R101-DCN, Modality=C+L+R2026.024,667—————1,2405,0303,1505,7605,8803,4004,1004,7202,9704,2004,8007,8403,5704,7305,2706,3506,330———————————
GaussianFormer3DMask=true, Backbone=R101-DCN, Modality=C+L2026.024,640—————9805,0003,1305,4005,9402,8103,6204,6202,6704,0204,9707,9103,7304,9005,5006,9106,760———————————
Inverse++Mask=false, Backbone=Res-101, Modality=C2026.023,104—————9564,1912,3534,2384,6351,8612,8032,6612,4772,5933,4816,0103,3233,7623,4831,9202,026———————————
CTF-OccMask=false, Backbone=Res-101, Modality=C2026.022,853—————8093,9332,0563,8294,2241,6932,4522,2722,1052,2983,1115,3333,3843,7983,3232,0791,800———————————
TPVFormerMask=false, Backbone=Res-101, Modality=C2026.022,834—————6673,9201,4244,1544,6981,9212,2641,7871,4543,0203,5515,6183,3653,5693,1611,9971,612———————————
RenderOccMask=false, Backbone=Swin-B, Modality=C2026.022,611—————4843,1721,0722,7672,6451,3871,8201,7671,7842,1192,3256,3203,6424,6214,4261,9582,072———————————
BEVStereoMask=false, Backbone=Res-101, Modality=C2026.022,451—————5733,8417883,8704,1201,7561,7331,4691,0311,6842,9625,4082,8923,2682,6541,8741,749———————————
BEVFormerMask=false, Backbone=Res-101, Modality=C2026.022,367—————5033,8799983,4414,1091,3241,6501,8151,7831,8662,7704,8952,7732,9082,5381,5411,446———————————
OccFormerMask=false, Backbone=Res-101, Modality=C2026.022,193—————5943,0291,2323,4403,9171,4441,6451,7229271,3902,6365,0993,0963,4662,273676697———————————
BEVDetMask=false, Backbone=Res-101, Modality=C2026.021,173—————2091,52904181,297135043136596665,2721,9042,6452,1781,4511,526———————————
MonoSceneMask=false, Backbone=Res-101, Modality=C2026.02606—————1757234264939385673983015904457171,491632792743101765———————————
CascadeOcc2026.0669.34—————54.8277.976.4172.2772.9651.0779.2179.2775.3461.2568.4884.168272.3769.6455.3546.3264.12——————————
OccWorld2026.0664.74—————46.3471.8469.9667.5969.0145.1473.574.7768.5754.6565.2782.7478.1869.8166.5352.9543.7761.88——————————
Gau-OccModality=C+L2026.0355.1—————14.861.240.765.368.137.549.658.443.751.355.484.548.358.560.371.568———————————
DAOccModality=Camera + LiDAR, Image Size=256 x 704, 2D Backbone=R502024.0954.33—7.8———1360.739.86466.536.34960.144.350.755.982.944.656.860.670.168.3———————————
DAOccModality=C+L2026.0354.3—————1360.739.86466.536.34960.144.350.755.982.944.656.860.670.168.3———————————
SurroundSDFBackbone=ConvNext-B, Image Size=640 x 1600, Test Time Augmentation=false2024.0353.01—————————————————————————————————
FB-OCC (Version K)backbone=InternImage-H, parameters=1200.0M2023.0752.79—————28.2856.744.3551.3761.8135.1247.3841.5639.8857.9648.3986.6656.9764.6661.2362.7852.35———————————
FB-OCCBackbone=InternImage-H, Image Size=960 x 1769, Test Time Augmentation=true2024.0352.79—————————————————————————————————
SDGOccModality=C+L2026.0351.7—————13.257.834.860.364.336.239.452.435.850.953.784.747.5586170.767.7———————————
SDGOCCModality=Camera + LiDAR, 2D Backbone=R502024.0951.66—7.5———13.257.824.360.364.336.239.452.435.850.953.784.647.55861.670.767.7———————————
UniOCCBackbone=ConvNext-B, Image Size=640 x 1600, Test Time Augmentation=false2024.0351.5—————————————————————————————————
ALOccModality=Camera, Image Size=512 x 1408, 2D Backbone=Swin-B, Temporal Fusion=16 frames2024.0950.6—1.5———1758.339.756.663.233.241.340.340.843.8518752.76265.257.750.9———————————
ALOCCModality=C2026.0350.6—————16.95537.556.962.932.43934.834.84150.18753.762.765.25750.9———————————
FB-OCC (Version J)backbone=ViT-L, adapter=ViT-Adapter, parameters=428.8M2023.0750.47—————16.7455.3339.7758.9461.7932.0442.6340.5139.0643.7251.3387.3453.7762.6366.0656.6349.74———————————
RadOccModality=C2026.0349.4—————15.655.9355262.433.138.132.633.239.54887.249.857.662.553.747.7———————————
RadOccModality=Camera + LiDAR, Image Size=512 x 1408, 2D Backbone=Swin-B2024.0949.38—————10.958.22557.962.93433.550.132.148.952.182.942.755.358.368.666———————————
FB-OCCModality=Camera, Image Size=960 x 1760, 2D Backbone=VoVNet-99, Temporal Fusion=16 frames2024.0948.9—————14.35738.357.762.134.439.438.839.442.9508650.260.162.552.445.7———————————
FB-OCC (Version I)backbone=VoVNet-99, input size=960x1760, voxel resolution=0.4m, parameters=130.8M2023.0748.9—————14.2657.0238.3457.6962.1234.3539.4338.8239.4242.9150.0286.0450.2460.0662.5452.3645.68———————————
FB-OCCModality=C2026.0348.9—————14.35738.357.762.134.439.438.839.442.9508650.260.162.552.445.7———————————
OccFusionModality=Camera + LiDAR, Image Size=900 x 1600, 2D Backbone=R1012024.0948.74—————12.451.83354.657.7344348.435.541.248.68344.757.16062.561.3———————————
OccFusionModality=C+L+R2026.0348.7—————14.251.833.35457.7344348.435.541.248.683.457.16062.561.344.9———————————
DAOccModality (train)=Camera+LiDAR, Modality (val)=Camera+LiDAR, Image Size=256 × 704, 2D Backbone=R502024.0948.348.47.844.548.951.9————————————————————————————
DAOccModality (train)=C+L, Modality (val)=C+L, Image Size=256 × 704, 2D Backbone=R502024.0948.348.47.844.548.951.9————————————————————————————
OccFusionModality=Camera + LiDAR + Radar, Image Size=900 x 1600, 2D Backbone=R101-DCN2024.0946.67—1———12.450.331.557.658.8344147.229.7424878.435.747.352.763.563.3———————————
LMPOcc-LHistory Frame=1, Resolution=512 × 1408, Backbone=SwinB2025.0446.61—————13.6853.8831.6553.1958.5330.6834.734.8634.639.4547.1785.0847.8558.1161.5657.3649.97———————————
COTRModality=Camera, Image Size=512 x 1408, 2D Backbone=Swin-B, Temporal Fusion=8 frames2024.0946.21—0.3———14.953.335.250.857.335.434.133.537.1394584.548.757.661.151.646.7———————————
COTRHistory Frame=8, Resolution=512 × 1408, Backbone=SwinB2025.0446.2—————14.8553.2535.1950.8357.2535.3634.0633.5437.1438.9944.9784.4648.7357.661.0851.6146.72———————————
COTRModality=C2026.0346.2—————14.953.335.250.857.434.133.531.933.139.14584.548.357.661.151.646.7———————————
SurroundSDFBackbone=ResNet101, Image Size=640 x 1600, Test Time Augmentation=false2024.0346—————————————————————————————————
LightOcc-LHistory Frame=1, Resolution=512 × 1408, Backbone=SwinB2025.0446—————14.552.2734.4553.7957.3331.835.8333.636.0939.8946.0984.2348.157.1460.0251.745.23———————————
DHD-LHistory Frame=1, Resolution=512 × 1408, Backbone=SwinB2025.0445.53—————14.0853.1232.3952.4457.3530.8335.2433.0133.4337.945.3484.6147.9657.3960.3252.2746.24———————————
STCOccModality=Camera, Image Size=512 x 1408, 2D Backbone=R50, Temporal Fusion=16 frames2024.0945—1.4———15.252.332.250.556.531.733.933.433.838.944.983.947.457.160.150.642.7———————————
STCOccModality=C2026.0345—————15.252.332.250.556.331.734.331.333.839.344.984.347.157.16152.446.3———————————
GEOccHistory Frame=8, Resolution=512 × 1408, Backbone=SwinB2025.0444.67—————14.0251.433.0852.0856.7230.0433.5432.3435.8339.3444.1883.4946.7755.7258.9448.8543———————————
COTR(+Dr.Occ)Backbone=R50, Input Size=704×256, Camera mask supervision=true2026.0344.1—————145332.645.854.929.731.530.935.73842.583.844.956.158.851.145.6———————————
OctreeOccImage Backbone=ResNet-101, Training with camera mask=true2023.1244.02——————51.729.9353.5256.7730.8333.1730.6529.9937.7643.8783.1744.5255.4558.8649.5246.33———————————
OctreeOccHistory Frame=4, Resolution=512 × 1408, Backbone=R1012025.0444.02—————11.9651.729.9353.5256.7730.8333.1730.6529.9937.7643.8783.1744.5255.4558.8649.5246.33———————————
FlashOccModality=Camera, Image Size=512 x 1408, 2D Backbone=Swin-B, Temporal Fusion=2 frames, EMA=true2024.0943.52—1.2———13.451.127.751.656.227.33029.929.837.843.583.846.656.259.650.844.7———————————
FlashOcc (M3)History Frame=1, Resolution=512 × 1408, Backbone=SwinB2025.0443.52—————13.4251.0727.6851.5756.2227.2729.9829.9329.837.7743.5283.8146.5556.1559.5650.8444.67———————————
FlashOccModality=C2026.0343.5—————13.451.832.154.158.329.932.831.929.938.746.28547.456.259.65043.7———————————
FB-OCCImage Backbone=ResNet-101, Training with camera mask=false2023.1243.41——————50.2332.3148.5552.8931.231.2530.7832.3337.0640.2283.3449.2757.1359.8847.6741.76———————————
FB-OccHistory Frame=4, Resolution=512 × 1408, Backbone=R1012025.0443.41—————12.150.2332.3148.5552.8931.231.2530.7832.3337.0640.2283.3449.2757.1359.8847.6741.76———————————
BEVDet4D(+Dr.Occ)Backbone=R50, Input Size=704×256, Camera mask supervision=true2026.0343.4—————14.952.830.745.655.130.330.83135.939.142.581.143.45457.64944.5———————————
BEVFormerBackbone=InterImage-XL, Image Size=640 x 1600, Test Time Augmentation=false2024.0343.3—————————————————————————————————
BEVDetBackbone=Swin-B, Image Size=640 x 1600, Test Time Augmentation=false2024.0343.1—————————————————————————————————
COTRBackbone=R50, Input Size=704×256, Camera mask supervision=true, Re-trained=true2026.0343.1—————12.851.630.345.454.930.430.43033.936.942.183.444.455.35849.644———————————
SurroundSDFBackbone=ResNet50, Image Size=256 x 704, Test Time Augmentation=false2024.0342.37—————————————————————————————————
PanoOccModality=Camera, Image Size=864 x 1600, 2D Backbone=R101-DCN, Temporal Fusion=4 frames2024.0942.13—3———11.750.529.649.455.523.333.330.63134.442.683.344.254.45645.940.4———————————
PanoOccImage Backbone=ResNet-101, Training with camera mask=true2023.1242.13——————50.4829.6449.4455.5223.2933.2630.5530.9934.4342.5783.3144.2354.456.0445.9440.4———————————
PanoOccHistory Frame=3, Resolution=512 × 1408, Backbone=R1012025.0442.13—————11.6750.4829.6449.4455.5223.2933.2630.5530.9934.4342.5783.3144.2354.456.0445.9440.4———————————
PanoOccModality=C2026.0342.1—————11.750.529.449.455.524.333.330.63134.442.683.344.254.45645.940.4———————————
FB-OCC (Version H)backbone=ResNet-50, test-time augmentation=true, parameters=67.8M2023.0742.06—————14.349.713046.6251.5429.329.1329.3530.4834.9739.3683.0747.1655.6259.8844.8939.58———————————
FB-OCCBackbone=ResNet50, Image Size=256 x 704, Test Time Augmentation=true2024.0342.06—————————————————————————————————
BEVDetOccModality=Camera, Image Size=512 x 1408, 2D Backbone=Swin-B, Temporal Fusion=2 frames2024.0942.02—1.2———12.249.625.15254.527.92828.927.236.442.282.343.354.657.948.643.6———————————
BEVDet4DImage Backbone=Swin-B, Training with camera mask=true2023.1242.02——————49.6325.152.0254.4627.8727.9928.9427.2336.4342.2282.3143.2954.4657.948.6143.55———————————
BEVDetOccModality=C2026.0342—————12.249.625.15254.527.92828.927.236.442.282.343.354.657.948.643.6———————————
ViewFormerBackbone=R50, Input Size=704×256, Camera mask supervision=true2026.0341.9—————12.950.127.944.652.922.429.62829.235.239.484.749.457.459.747.440.6———————————
OSPBackbone=R101, Input Size=1600×900, Camera mask supervision=true2026.0341.2—————10.94927.750.255.922.93130.930.335.631.282.142.651.955.144.838.2———————————
SurroundOccBackbone=InterImage-B, Image Size=640 x 1600, Test Time Augmentation=false2024.0340.7—————————————————————————————————
FB-OCC (Version G)backbone=ResNet-50, dice loss=true, 3d transformation alignment=true2023.0740.69—————14.4145.7729.1945.2950.5327.8629.0128.1528.61—37.8681.7645.5253.9958.6943.4938.75———————————
FB-OCCBackbone=ResNet50, Image Size=256 x 704, Test Time Augmentation=false2024.0340.69—————————————————————————————————
BEVFormerBackbone=ResNet101, Image Size=900 x 1600, Test Time Augmentation=false2024.0340.6—————————————————————————————————
VoxFormerBackbone=ResNet101, Image Size=900 x 1600, Test Time Augmentation=false2024.0340.6—————————————————————————————————
MiLOBackbone=ResNet50, Image Size=256 x 704, Test Time Augmentation=false2024.0340.49—————————————————————————————————
LMPOcc-SHistory Frame=✗, Resolution=256 × 704, Backbone=R502025.0440.38—————10.9748.8723.6643.3151.2723.6123.7927.4926.2836.2637.9581.9742.0652.0958.4352.9645.45———————————
FB-OCC (Version F)backbone=ResNet-50, joint depth/semantic pre-training=true2023.0739.89—————13.6645.8828.2644.9149.7826.2128.8428.2727.8932.7537.5681.243.4652.1356.3542.7938.1———————————
UniOCCBackbone=ResNet50, Image Size=256 x 704, Test Time Augmentation=false2024.0339.7—————————————————————————————————
BEVDetOcc(8F)Modality (train)=Camera+LiDAR, Modality (val)=Camera, Image Size=384 × 704, 2D Backbone=R50, Temporal Frames=8F2024.0939.332.6—26.633.138.2————————————————————————————
BEVDetOcc(8F)Modality (train)=C+L, Modality (val)=C, Image Size=384 × 704, 2D Backbone=R502024.0939.332.6—26.633.138.2————————————————————————————
FastOccHistory Frame=16, Resolution=640 × 1600, Backbone=R1012025.0439.21—————12.0643.5328.0444.852.1622.9629.1429.6826.9830.8138.4482.0441.9351.9253.7141.0435.49———————————
BEVFormer(4F)Modality (train)=Camera, Image Size=900 × 1600, 2D Backbone=R101, Temporal Frames=4F2024.0939.232.4—26.132.938————————————————————————————
BEVFormer(4F)Modality (train)=C, Image Size=900 × 1600, 2D Backbone=R1012024.0939.232.4—26.132.938————————————————————————————
FB-OCC (Version E)backbone=ResNet-50, temporal frames=162023.0739.11—————13.5744.7427.0145.4149.125.1526.3327.8627.7932.2836.7580.0742.7651.1855.1342.1937.53———————————
FB-Occ(16F)Modality (train)=Camera+LiDAR, Modality (val)=Camera, Image Size=256 × 704, 2D Backbone=R50, Temporal Frames=16F2024.0939.133.5—26.734.139.7————————————————————————————
FB-Occ(16F)Modality (train)=C+L, Modality (val)=C, Image Size=256 × 704, 2D Backbone=R502024.0939.133.5—26.734.139.7————————————————————————————
BEVStereoBackbone=ResNet50, Image Size=384 x 704, Test Time Augmentation=false2024.0339.1—————————————————————————————————
FB-OccBackbone=R50, Input Size=704×256, Camera mask supervision=true2026.0339.1—————13.644.72745.449.125.226.327.927.832.336.880.142.851.255.142.237.5———————————
ALOcc(16F)Modality (train)=Camera+LiDAR, Modality (val)=Camera, Image Size=256 × 704, 2D Backbone=R50, Temporal Frames=16F2024.093843.7637.844.748.8————————————————————————————
ALOcc(16F)Modality (train)=C+L, Modality (val)=C, Image Size=256 × 704, 2D Backbone=R502024.093843.7637.844.748.8————————————————————————————