List your company

Semantic Segmentation on nuScenes

79.5mIoU (Average)SphereFormer
16.78833.06949.3565.631Mar 21, 2023Sep 20, 2023Mar 21, 2024Sep 21, 2024Mar 23, 2025Sep 22, 2025Mar 25, 2026

Evaluation results

MethodLinks
SphereFormerTime (ms)=59, GPU (GB)=0.81, Param (M)=32.3, Hardware=Nvidia RTX 3090 GPU, Batch size=12023.0379.5—————78.746.795.293.75488.981.16874.286.297.274.376.375.891.489.7
OA-CNNs2024.0378.9—————————————————————
SphereFormer2024.0378.4—————————————————————
CurveCloudNetType=Curve, Time (ms)=87, GPU (GB)=1.14, Param (M)=28.8, Hardware=Nvidia RTX 3090 GPU, Batch size=12023.0378—————77.345.792.491.959.484.578.564.169.68596.972.775.675.290.589
SPVNAS2024.0377.4—————————————————————
MinkowskiNetType=Voxel, Time (ms)=44, GPU (GB)=0.29, Param (M)=36.6, Hardware=Nvidia RTX 3090 GPU, Batch size=12023.0376.2—————75.443.991.9934984.378.364.665.985.796.171.567.574.886.584.9
Cylinder3DTime (ms)=80, GPU (GB)=1.57, Param (M)=55.9, Hardware=Nvidia RTX 3090 GPU, Batch size=12023.0376.1—————76.440.391.293.851.37878.964.962.184.496.871.676.475.490.587.4
Cylinder3D2024.0376.1—————————————————————
SparseUNet2024.0373.3—————————————————————
PolarNetHardware=Nvidia RTX 3090 GPU, Batch size=12023.0371—————74.728.285.390.935.177.571.358.857.476.196.571.174.77487.385.7
PointMLPType=Point, Time (ms)=164, GPU (GB)=4.94, Param (M)=16.8, Hardware=Nvidia RTX 3090 GPU, Batch size=12023.0367.9—————72.327.888.286.337.25160.750.656.471.195.770.670.97288.887.2
DINOv3 + CDArch.=ViT-H+/16, Evaluation Protocol=linear probing2026.0265.4—————————————————————
PointNextType=Point, Time (ms)=155, GPU (GB)=0.62, Param (M)=41.5, Hardware=Nvidia RTX 3090 GPU, Batch size=12023.0365—————68.71.286.987.541.857.454.334.955.375.195.768.970.271.586.584
DINOv3Arch.=ViT-H+/16, Evaluation Protocol=linear probing2026.0264.5—————————————————————
RandLA-NetType=Point, Time (ms)=21, GPU (GB)=0.18, Param (M)=1.2, Hardware=Nvidia RTX 3090 GPU, Batch size=12023.0362.9—————72.512.636.681.838.772.368.537.344.759.795.38769.771.173.285.9
DepthAnythingV2 + CDArch.=ViT-B/14, Evaluation Protocol=linear probing2026.0255.1—————————————————————
DepthAnythingV2Arch.=ViT-B/14, Evaluation Protocol=linear probing2026.0253.5—————————————————————
PointNet++Type=Point, Time (ms)=274, GPU (GB)=0.6, Param (M)=1.5, Hardware=Nvidia RTX 3090 GPU, Batch size=12023.0351.1—————60.16.558.466.316.42050.812.631.5429460.863.869.282.482.3
IBOT + CDArch.=ViT-L/16, Evaluation Protocol=linear probing2026.0249.3—————————————————————
CLIP + CDArch.=ViT-B/16, Evaluation Protocol=linear probing2026.0249.2—————————————————————
DINO + CDArch.=ViT-B/8, Evaluation Protocol=linear probing2026.0248.5—————————————————————
IBOTArch.=ViT-L/16, Evaluation Protocol=linear probing2026.0247.5—————————————————————
DINO + CDArch.=ResNet502026.0246.1—————————————————————
DINO + CDArch.=ResNet50, Evaluation Protocol=linear probing2026.0246.1—————————————————————
CLIPArch.=ViT-B/16, Evaluation Protocol=linear probing2026.0245.8—————————————————————
DistillBEVArch.=ResNet502026.0244.9—————————————————————
DINOArch.=ViT-B/8, Evaluation Protocol=linear probing2026.0244.7—————————————————————
MoCov2 + CDArch.=ResNet50, Evaluation Protocol=linear probing2026.0241.4—————————————————————
MoCov2Arch.=ResNet50, Evaluation Protocol=linear probing2026.0238.7—————————————————————
DINOArch.=ResNet502026.0238.4—————————————————————
DINOArch.=ResNet50, Evaluation Protocol=linear probing2026.0238.4—————————————————————
MoVieDriveDiverse conditions?=✓, Multi-modal?=✓2025.0837.5—————————————————————
BEVDistillArch.=ResNet502026.0236.1—————————————————————
CogVideoX + SyntheOccDiverse conditions?=✓, Multi-modal?=✗2025.0832.4—————————————————————
MagicDriveDiverse conditions?=✓, Multi-modal?=✗2025.0823.5—————————————————————
Le MuMo JEPA2026.0322.8—————————————————————
MagicDrive-V2Diverse conditions?=✓, Multi-modal?=✗2025.0822.4—————————————————————
ImageBind2026.0319.8—————————————————————
MultiMAE-SS2026.0319.5—————————————————————
MultiMAE-MT2026.0319.2—————————————————————
ALSOBackbone=MinkUNet [74]2022.12—26.237.45969.871.8————————————————
ALSOBackbone=SPVCNN [78]2022.12—24.837.458.469.571.3————————————————
DepthContrastBackbone=MinkUNet [74]2022.12—21.734.657.469.271.2————————————————
No pre-trainingBackbone=MinkUNet [74]2022.12—21.63557.36971.2————————————————
No pre-trainingBackbone=SPVCNN [78]2022.12—22.234.457.16970.7————————————————
PointContrastBackbone=MinkUNet [74]2022.12—27.13758.969.471.1————————————————