Alert button
Picture for Yash Bhalgat

Yash Bhalgat

Alert button

N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields

Mar 16, 2024
Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi

Viaarxiv icon

SiLVR: Scalable Lidar-Visual Reconstruction with Neural Radiance Fields for Robotic Inspection

Mar 11, 2024
Yifu Tao, Yash Bhalgat, Lanke Frank Tarimo Fu, Matias Mattamala, Nived Chebrolu, Maurice Fallon

Viaarxiv icon

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

Jun 07, 2023
Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi

Figure 1 for Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
Figure 2 for Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
Figure 3 for Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
Figure 4 for Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
Viaarxiv icon

Refinement for Absolute Pose Regression with Neural Feature Synthesis

Mar 17, 2023
Shuai Chen, Yash Bhalgat, Xinghui Li, Jiawang Bian, Kejie Li, Zirui Wang, Victor Adrian Prisacariu

Figure 1 for Refinement for Absolute Pose Regression with Neural Feature Synthesis
Figure 2 for Refinement for Absolute Pose Regression with Neural Feature Synthesis
Figure 3 for Refinement for Absolute Pose Regression with Neural Feature Synthesis
Figure 4 for Refinement for Absolute Pose Regression with Neural Feature Synthesis
Viaarxiv icon

A Light Touch Approach to Teaching Transformers Multi-view Geometry

Nov 28, 2022
Yash Bhalgat, Joao F. Henriques, Andrew Zisserman

Figure 1 for A Light Touch Approach to Teaching Transformers Multi-view Geometry
Figure 2 for A Light Touch Approach to Teaching Transformers Multi-view Geometry
Figure 3 for A Light Touch Approach to Teaching Transformers Multi-view Geometry
Figure 4 for A Light Touch Approach to Teaching Transformers Multi-view Geometry
Viaarxiv icon

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning

Apr 01, 2022
Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat, Wonsuk Yang, Hannah Rose Kirk, Aleksandar Shtedritski, Max Bain

Figure 1 for A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Figure 2 for A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Figure 3 for A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Figure 4 for A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Viaarxiv icon

Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation

Nov 11, 2021
John Yang, Yash Bhalgat, Simyung Chang, Fatih Porikli, Nojun Kwak

Figure 1 for Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation
Figure 2 for Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation
Figure 3 for Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation
Figure 4 for Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation
Viaarxiv icon

Data-driven Weight Initialization with Sylvester Solvers

May 02, 2021
Debasmit Das, Yash Bhalgat, Fatih Porikli

Figure 1 for Data-driven Weight Initialization with Sylvester Solvers
Figure 2 for Data-driven Weight Initialization with Sylvester Solvers
Figure 3 for Data-driven Weight Initialization with Sylvester Solvers
Figure 4 for Data-driven Weight Initialization with Sylvester Solvers
Viaarxiv icon

Structured Convolutions for Efficient Neural Network Design

Aug 06, 2020
Yash Bhalgat, Yizhe Zhang, Jamie Lin, Fatih Porikli

Figure 1 for Structured Convolutions for Efficient Neural Network Design
Figure 2 for Structured Convolutions for Efficient Neural Network Design
Figure 3 for Structured Convolutions for Efficient Neural Network Design
Figure 4 for Structured Convolutions for Efficient Neural Network Design
Viaarxiv icon

LSQ+: Improving low-bit quantization through learnable offsets and better initialization

Apr 20, 2020
Yash Bhalgat, Jinwon Lee, Markus Nagel, Tijmen Blankevoort, Nojun Kwak

Figure 1 for LSQ+: Improving low-bit quantization through learnable offsets and better initialization
Figure 2 for LSQ+: Improving low-bit quantization through learnable offsets and better initialization
Figure 3 for LSQ+: Improving low-bit quantization through learnable offsets and better initialization
Figure 4 for LSQ+: Improving low-bit quantization through learnable offsets and better initialization
Viaarxiv icon