Bohan Li

8

Papers

100

Total Citations

Papers (8)

Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion

Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification

DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

Closed-Loop Unsupervised Representation Disentanglement with $\beta$-VAE Distillation and Diffusion Probabilistic Feedback

One at a Time: Progressive Multi-Step Volumetric Probability Learning for Reliable 3D Scene Perception

Hybrid-grained Feature Aggregation with Coare-to-fine Language Guidance for Self-supervised Monocular Depth Estimation

Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism

UniScene: Unified Occupancy-centric Driving Scene Generation