Picture for David Acuna

David Acuna

Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models

Add code
Sep 15, 2024
Figure 1 for Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
Figure 2 for Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
Figure 3 for Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
Figure 4 for Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
Viaarxiv icon

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering

Add code
Aug 19, 2024
Figure 1 for Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
Figure 2 for Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
Figure 3 for Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
Figure 4 for Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
Viaarxiv icon

RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting

Add code
Apr 16, 2024
Viaarxiv icon

Can Feedback Enhance Semantic Grounding in Large Vision-Language Models?

Add code
Apr 09, 2024
Viaarxiv icon

DreamTeacher: Pretraining Image Backbones with Deep Generative Models

Add code
Jul 14, 2023
Viaarxiv icon

Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting

Add code
Feb 09, 2023
Figure 1 for Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting
Figure 2 for Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting
Figure 3 for Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting
Figure 4 for Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting
Viaarxiv icon

Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion

Add code
Aug 19, 2022
Figure 1 for Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion
Figure 2 for Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion
Figure 3 for Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion
Figure 4 for Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion
Viaarxiv icon

How Much More Data Do I Need? Estimating Requirements for Downstream Tasks

Add code
Jul 13, 2022
Figure 1 for How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
Figure 2 for How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
Figure 3 for How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
Figure 4 for How Much More Data Do I Need? Estimating Requirements for Downstream Tasks
Viaarxiv icon

Scalable Neural Data Server: A Data Recommender for Transfer Learning

Add code
Jun 19, 2022
Figure 1 for Scalable Neural Data Server: A Data Recommender for Transfer Learning
Figure 2 for Scalable Neural Data Server: A Data Recommender for Transfer Learning
Figure 3 for Scalable Neural Data Server: A Data Recommender for Transfer Learning
Figure 4 for Scalable Neural Data Server: A Data Recommender for Transfer Learning
Viaarxiv icon

Domain Adversarial Training: A Game Perspective

Add code
Feb 10, 2022
Figure 1 for Domain Adversarial Training: A Game Perspective
Figure 2 for Domain Adversarial Training: A Game Perspective
Figure 3 for Domain Adversarial Training: A Game Perspective
Figure 4 for Domain Adversarial Training: A Game Perspective
Viaarxiv icon