Michael Bi Mi

papers

839

total citations

papers (12)

PoseTriplet: Co-Evolving 3D Human Pose Estimation, Imitation, and Hallucination Under Self-Supervision

CVPR 2022arXiv

citations

Enhancing Video Super-Resolution via Implicit Resampling-based Alignment

CVPR 2024arXiv

citations

Point2Seq: Detecting 3D Objects As Sequences

CVPR 2022arXiv

citations

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

ICCV 2023arXiv

citations

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

AAAI 2024arXiv

citations

Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention

AAAI 2024arXiv

citations

Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction

CVPR 2023arXiv

citations

Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning

AAAI 2025

citations

Michael Bi Mi

papers (12)

DepGraph: Towards Any Structural Pruning

TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration

ONCE-3DLanes: Building Monocular 3D Lane Detection

Priority-Centric Human Motion Generation in Discrete Latent Space

PoseTriplet: Co-Evolving 3D Human Pose Estimation, Imitation, and Hallucination Under Self-Supervision

Enhancing Video Super-Resolution via Implicit Resampling-based Alignment

Point2Seq: Detecting 3D Objects As Sequences

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention

Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction

Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning

papers (12)

DepGraph: Towards Any Structural Pruning

TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration

ONCE-3DLanes: Building Monocular 3D Lane Detection

Priority-Centric Human Motion Generation in Discrete Latent Space

PoseTriplet: Co-Evolving 3D Human Pose Estimation, Imitation, and Hallucination Under Self-Supervision

Enhancing Video Super-Resolution via Implicit Resampling-based Alignment

Point2Seq: Detecting 3D Objects As Sequences

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention

Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction

Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning