Gordon Wetzstein

66

Papers

1,191

Total Citations

Papers (66)

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

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

FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views

TC4D: Trajectory-Conditioned Text-to-4D Generation

Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models

NeurIPS 2025arXiv

Long-Context State-Space Video World Models

Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models

Textured Gaussians for Enhanced 3D Scene Appearance Modeling

X-Dyna: Expressive Dynamic Human Image Animation

Gaussian Mixture Flow Matching Models

PixelRNN: In-pixel Recurrent Neural Networks for End-to-end–optimized Perception with Neural Sensors

GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography

AIpparel: A Multimodal Foundation Model for Digital Garments

Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors

GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

Geometric Algebra Planes: Convex Implicit Neural Volumes

Acoustic Non-Line-Of-Sight Imaging

LiFF: Light Field Features in Scale and Depth

Deep Optics for Single-Shot High-Dynamic-Range Imaging

Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform

AutoInt: Automatic Integration for Fast Neural Volume Rendering

Pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis

Neural Lumigraph Rendering

Efficient Geometry-Aware 3D Generative Adversarial Networks

BACON: Band-Limited Coordinate Networks for Multiscale Scene Representation

3D Neural Field Generation Using Triplane Diffusion

SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene

PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields

PointAvatar: Deformable Point-Based Head Avatars From Videos

ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction

Deep Optics for Monocular Depth Estimation and 3D Object Detection

Time-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systems

Single-Shot Hyperspectral-Depth Imaging With Learned Diffractive Optics

CC3D: Layout-Conditioned Generation of Compositional 3D Scenes

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking

Generative Novel View Synthesis with 3D-Aware Diffusion Models

DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models

Disambiguating Monocular Depth Estimation with a Single Transient

CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Images

Consensus Convolutional Sparse Coding

The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion

Diffusion Self-Distillation for Zero-Shot Customized Image Generation

ImageGem: In-the-wild Generative Image Interaction Dataset for Generative Model Personalization

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

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions

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

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

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

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

Orthogonal Adaptation for Modular Customization of Diffusion Models

Gaussian Shell Maps for Efficient 3D Human Generation

Fast and Flexible Convolutional Sparse Coding

Variable Aperture Light Field Photography: Overcoming the Diffraction-Limited Spatio-Angular Resolution Tradeoff

Reconstructing Transient Images From Single-Photon Sensors

A Wide-Field-Of-View Monocentric Light Field Camera

Deep End-to-End Time-of-Flight Imaging

DeepVoxels: Learning Persistent 3D Feature Embeddings

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

Implicit Neural Representations with Periodic Activation Functions

MetaSDF: Meta-Learning Signed Distance Functions

Fast Training of Neural Lumigraph Representations using Meta Learning

Amortized Inference for Heterogeneous Reconstruction in Cryo-EM

NeuForm: Adaptive Overfitting for Neural Shape Editing

Generative Neural Articulated Radiance Fields