David Novotny

28

Papers

10

Total Citations

Papers (28)

UnCommon Objects in 3D

Twinner: Shining Light on Digital Twins in a Few Snaps

VGGT: Visual Geometry Grounded Transformer

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models

AnchorNet: A Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching

Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection

Unsupervised Learning of 3D Object Categories From Videos in the Wild

NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go

Discovering Relationships Between Object Categories via Universal Canonical Maps

KeyTr: Keypoint Transporter for 3D Reconstruction of Deformable Objects in Videos

HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images

Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories

Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection

Learning 3D Object Categories by Looking Around Them

C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion

DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension

Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category Reconstruction

Replay: Multi-modal Multi-view Acted Videos for Casual Holography

PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

HoloFusion: Towards Photo-realistic 3D Generative Modeling

LIM: Large Interpolator Model for Dynamic Reconstruction

PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models

Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels

PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments

Continuous Surface Embeddings

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction