Michael Bi Mi
22 papers · 2022–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (46) π€ Dynamic Duo (11)
β‘
Prolific Year Β· Prolific
ποΈ
Keyword Collector
(100)
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Deep Learning
(15)
Computer Vision
(14)
Machine Learning
(12)
Analysis
(12)
Application Areas
(7)
Learning Types Β· Deep Learning
(7)
Architectures
(6)
Learning Types Β· Machine Learning
(5)
Models
(4)
Domain-Specific
(3)
Processing
(3)
Generation
(2)
Techniques
(2)
Artificial Intelligence
(1)
Reinforcement Learning
(1)
Keywords
semantic segmentation
(4)
point cloud
(3)
weakly supervised learning
(2)
model compression
(2)
diffusion model
(2)
self-supervised learning
(2)
adverse weather
(2)
domain adaptation
(2)
teacher-student learning
(2)
image restoration
(2)
autonomous driving
(1)
scene understanding
(1)
continual learning
(1)
sequence modeling
(1)
bird's eye view
(1)
reinforcement learning
(1)
hand pose estimation
(1)
scene reconstruction
(1)
ordinal regression
(1)
video super-resolution
(1)
Papers
AnchorSplat: Feed-Forward 3D Gaussian Splatting With 3D Geometric Priors
CVPR 2026
Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning
AAAI 2025
DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators
ECCV 2024
End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning
NeurIPS 2024
Enhancing Video Super-Resolution via Implicit Resampling-based Alignment
CVPR 2024
HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping
AAAI 2024
Isomorphic Pruning for Vision Models
ECCV 2024
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
NeurIPS 2024
MetaISP: Efficient RAW-to-sRGB Mappings with Merely 1M Parameters
IJCAI 2024
MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation
AAAI 2024
Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
AAAI 2024
Vista3D: unravel the 3d darkside of a single image
ECCV 2024
DepGraph: Towards Any Structural Pruning
CVPR 2023
GhostRNN: Reducing State Redundancy in RNN with Cheap Operations
Interspeech 2023
Improving Deep Regression with Ordinal Entropy
ICLR 2023
Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction
CVPR 2023
PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
ICCV 2023
Priority-Centric Human Motion Generation in Discrete Latent Space
ICCV 2023
TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration
ICCV 2023
ONCE-3DLanes: Building Monocular 3D Lane Detection
CVPR 2022
Point2Seq: Detecting 3D Objects As Sequences
CVPR 2022
PoseTriplet: Co-Evolving 3D Human Pose Estimation, Imitation, and Hallucination Under Self-Supervision
CVPR 2022