Picture for Yikang Ding

Yikang Ding

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

Add code
Mar 19, 2025
Viaarxiv icon

MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction

Add code
Mar 13, 2025
Viaarxiv icon

HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

Add code
Jan 24, 2025
Figure 1 for HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
Figure 2 for HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
Figure 3 for HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
Figure 4 for HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
Viaarxiv icon

UniScene: Unified Occupancy-centric Driving Scene Generation

Add code
Dec 06, 2024
Viaarxiv icon

M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation

Add code
May 03, 2024
Figure 1 for M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation
Figure 2 for M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation
Figure 3 for M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation
Figure 4 for M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation
Viaarxiv icon

The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion

Add code
Mar 30, 2024
Viaarxiv icon

OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction

Add code
Feb 28, 2024
Figure 1 for OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction
Figure 2 for OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction
Figure 3 for OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction
Figure 4 for OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction
Viaarxiv icon

LayerDiffusion: Layered Controlled Image Editing with Diffusion Models

Add code
May 30, 2023
Viaarxiv icon

Rethinking Dimensionality Reduction in Grid-based 3D Object Detection

Add code
Sep 24, 2022
Figure 1 for Rethinking Dimensionality Reduction in Grid-based 3D Object Detection
Figure 2 for Rethinking Dimensionality Reduction in Grid-based 3D Object Detection
Figure 3 for Rethinking Dimensionality Reduction in Grid-based 3D Object Detection
Figure 4 for Rethinking Dimensionality Reduction in Grid-based 3D Object Detection
Viaarxiv icon

KD-MVS: Knowledge Distillation Based Self-supervised Learning for MVS

Add code
Jul 21, 2022
Figure 1 for KD-MVS: Knowledge Distillation Based Self-supervised Learning for MVS
Figure 2 for KD-MVS: Knowledge Distillation Based Self-supervised Learning for MVS
Figure 3 for KD-MVS: Knowledge Distillation Based Self-supervised Learning for MVS
Figure 4 for KD-MVS: Knowledge Distillation Based Self-supervised Learning for MVS
Viaarxiv icon