Andrea Tagliasacchi

49

Papers

1,062

Total Citations

Papers (49)

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

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

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields

AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers

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

Unsupervised Keypoints from Pretrained Diffusion Models

Accelerating Neural Field Training via Soft Mining

RoMo: Robust Motion Segmentation Improves Structure from Motion

SMITE: Segment Me In TimE

StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting

PIAD: Pose and Illumination agnostic Anomaly Detection

LOLNerf: Learn From One Look

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

Urban Radiance Fields

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

MetaPose: Fast 3D Pose From Multiple Views Without 3D Supervision

Kubric: A Scalable Dataset Generator

BlendFields: Few-Shot Example-Driven Facial Modeling

SparsePose: Sparse-View Camera Pose Regression and Refinement

OpenScene: 3D Scene Understanding With Open Vocabularies

NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization

CUF: Continuous Upsampling Filters

MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures

Low-Dimensionality Calibration Through Local Anisotropic Scaling for Robust Hand Model Personalization

Linearized Multi-Sampling for Differentiable Image Transformation

COTR: Correspondence Transformer for Matching Across Images

Vector Neurons: A General Framework for SO(3)-Equivariant Networks

CC3D: Layout-Conditioned Generation of Compositional 3D Scenes

NASA Neural Articulated Shape Approximation

RobustNeRF: Ignoring Distractors With Robust Losses

Radiant Foam: Real-Time Differentiable Ray Tracing

Neural Fields as Distributions: Signal Processing Beyond Euclidean Space

BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction

Volumetric Capture of Humans With a Single RGBD Camera via Semi-Parametric Learning

CvxNet: Learnable Convex Decomposition

Deep Implicit Volume Compression

BSP-Net: Generating Compact Meshes via Binary Space Partitioning

ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning

MIST: Multiple Instance Spatial Transformer

DeRF: Decomposed Radiance Fields

CoNeRF: Controllable Neural Radiance Fields

ShapeFlow: Learnable Deformation Flows Among 3D Shapes

CoSE: Compositional Stroke Embeddings

PIE-NET: Parametric Inference of Point Cloud Edges

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

D^2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video

Unsupervised Semantic Correspondence Using Stable Diffusion

Neural Fields with Hard Constraints of Arbitrary Differential Order