Picture for Bharath Hariharan

Bharath Hariharan

Cornell University

Towards LLM Agents for Earth Observation

Add code
Apr 16, 2025
Viaarxiv icon

FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution

Add code
Apr 09, 2025
Viaarxiv icon

Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X Collaboration

Add code
Feb 19, 2025
Viaarxiv icon

Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scene

Add code
Feb 10, 2025
Viaarxiv icon

Video Creation by Demonstration

Add code
Dec 12, 2024
Figure 1 for Video Creation by Demonstration
Figure 2 for Video Creation by Demonstration
Figure 3 for Video Creation by Demonstration
Figure 4 for Video Creation by Demonstration
Viaarxiv icon

Generating 3D-Consistent Videos from Unposed Internet Photos

Add code
Nov 20, 2024
Figure 1 for Generating 3D-Consistent Videos from Unposed Internet Photos
Figure 2 for Generating 3D-Consistent Videos from Unposed Internet Photos
Figure 3 for Generating 3D-Consistent Videos from Unposed Internet Photos
Figure 4 for Generating 3D-Consistent Videos from Unposed Internet Photos
Viaarxiv icon

AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery

Add code
Oct 31, 2024
Figure 1 for AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery
Figure 2 for AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery
Figure 3 for AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery
Figure 4 for AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery
Viaarxiv icon

Scale-Aware Recognition in Satellite Images under Resource Constraint

Add code
Oct 31, 2024
Viaarxiv icon

Learning 3D Perception from Others' Predictions

Add code
Oct 03, 2024
Figure 1 for Learning 3D Perception from Others' Predictions
Figure 2 for Learning 3D Perception from Others' Predictions
Figure 3 for Learning 3D Perception from Others' Predictions
Figure 4 for Learning 3D Perception from Others' Predictions
Viaarxiv icon

Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning

Add code
Sep 30, 2024
Viaarxiv icon