Angjoo Kanazawa

55

Papers

411

Total Citations

Papers (55)

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

GARField: Group Anything with Radiance Fields

From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations

Generative Proxemics: A Prior for 3D Social Interaction from Images

Estimating Body and Hand Motion in an Ego‑sensed World

Reconstructing People, Places, and Cameras

Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding

NeRFiller: Completing Scenes via Generative 3D Inpainting

The More You See in 2D the More You Perceive in 3D

WarpNet: Weakly Supervised Matching for Single-View Reconstruction

3D Menagerie: Modeling the 3D Shape and Pose of Animals

Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape From Images

SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild'

End-to-End Recovery of Human Shape and Pose

Learning 3D Human Dynamics From Video

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control

pixelNeRF: Neural Radiance Fields From One or Few Images

De-Rendering the World's Revolutionary Artefacts

Human Mesh Recovery From Multiple Shots

Tracking People by Predicting 3D Appearance, Location and Pose

Deformable Sprites for Unsupervised Video Decomposition

Learning To Listen: Modeling Non-Deterministic Dyadic Facial Motion

Plenoxels: Radiance Fields Without Neural Networks

On the Benefits of 3D Pose and Tracking for Human Action Recognition

K-Planes: Explicit Radiance Fields in Space, Time, and Appearance

Decoupling Human and Camera Motion From Videos in the Wild

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture From Images "In the Wild"

Predicting 3D Human Dynamics From Video

PlenOctrees for Real-Time Rendering of Neural Radiance Fields

AI Choreographer: Music Conditioned 3D Dance Generation With AIST++

Infinite Nature: Perpetual View Generation of Natural Scenes From a Single Image

Reconstructing Hand-Object Interactions in the Wild

Humans in 4D: Reconstructing and Tracking Humans with Transformers

Can Language Models Learn to Listen?

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions

Continuous 3D Perception Model with Persistent State

LERF: Language Embedded Radiance Fields

NerfAcc: Efficient Sampling Accelerates NeRFs

Shape and Viewpoint without Keypoints

InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images

Studying Bias in GANs through the Lens of Race

TAVA: Template-Free Animatable Volumetric Actors

The One Where They Reconstructed 3D Humans and Environments in TV Shows

Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs

MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos

Segment Any Motion in Videos

Decentralized Diffusion Models

St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World

Shape of Motion: 4D Reconstruction from a Single Video

Reconstructing Hands in 3D with Transformers

An Analysis of SVD for Deep Rotation Estimation

Tracking People with 3D Representations

Monocular Dynamic View Synthesis: A Reality Check

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives