Kyle Genova

16

Papers

80

Total Citations

Papers (16)

NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis

MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images

Unsupervised Training for 3D Morphable Model Regression

CvxNet: Learnable Convex Decomposition

Local Deep Implicit Functions for 3D Shape

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation

IBRNet: Learning Multi-View Image-Based Rendering

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

OpenScene: 3D Scene Understanding With Open Vocabularies

Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision

Learning Shape Templates With Structured Implicit Functions

Multiresolution Deep Implicit Functions for 3D Shape Representation

Differentiable Surface Rendering via Non-Differentiable Sampling

SplatTalk: 3D VQA with Gaussian Splatting

Polynomial Neural Fields for Subband Decomposition and Manipulation