Leonidas Guibas

29

Papers

1,045

Total Citations

Papers (29)

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

Probing the 3D Awareness of Visual Foundation Models

NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis

Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects

Category-Level Multi-Part Multi-Joint 3D Shape Assembly

AllTracker: Efficient Dense Point Tracking at High Resolution

SuperDec: 3D Scene Decomposition with Superquadrics Primitives

FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement

AIpparel: A Multimodal Foundation Model for Digital Garments

SceneCrafter: Controllable Multi-View Driving Scene Editing

GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

LookOut: Real-World Humanoid Egocentric Navigation

MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps

CurveCloudNet: Processing Point Clouds with 1D Structure

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

BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing

MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds

Diffusion Self-Distillation for Zero-Shot Customized Image Generation

Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation

SplatTalk: 3D VQA with Gaussian Splatting

CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization

Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

Self-Calibrating Gaussian Splatting for Large Field-of-View Reconstruction

HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild

NeurIPS 2025arXiv

GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation

MultiPhys: Multi-Person Physics-aware 3D Motion Estimation

CAD: Photorealistic 3D Generation via Adversarial Distillation