Zhenyu Li
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
arXiv 2026
Depth Anything 3: Recovering the Visual Space from Any Views
arXiv 2025
Bridging Text and Vision: A Multi-View Text-Vision Registration Approach for Cross-Modal Place Recognition
arXiv 2025
FocusLLM: Precise Understanding of Long Context by Dynamic Condensing
arXiv 2024
StereoCrafter-Zero: Zero-Shot Stereo Video Generation with Noisy Restart
arXiv 2024
ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning
arXiv 2024
PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation
CVPR 2024 1
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
arXiv 2023
Affiliations
Frequent co-authors
10from 8 papers