← Authors

David Novotny

34 papers · 2015–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (10) 🐝 Cross-Pollinator (6) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (46) 🀝 Dynamic Duo (25) πŸ”¬ Deep Specialist (22) πŸš€ Conference Pioneer πŸ’Ž Century Club (34) πŸ—ƒοΈ Keyword Collector (139) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (9) ⚑ Prolific Year (5)

Conferences

CVPR (15) ICCV (8) NIPS (6) ECCV (3) RSS (1) WACV (1)

Top co-authors

Andrea Vedaldi (25) Roman Shapovalov (12) Natalia Neverova (11) Patrick Labatut (6) Tom Monnier (5) Jianyuan Wang (5) Niloy J. Mitra (4) Ben Graham (4) Ignacio Rocco (4) Jeremy Reizenstein (4)

Keywords

3d reconstruction (18) depth estimation (4) view synthesis (4) neural network (4) 3d vision (4) diffusion model (4) deformable object (3) representation learning (3) point cloud (3) camera pose estimation (3) unsupervised learning (3) self-supervised learning (3) dense correspondence (3) neural radiance field (2) 3d generation (2) shape correspondence (2) camera pose (2) video understanding (2) semantic matching (2) pose estimation (2)

Papers

Twinner: Shining Light on Digital Twins in a Few Snaps CVPR 2025
UnCommon Objects in 3D CVPR 2025
VGGT: Visual Geometry Grounded Transformer CVPR 2025
PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models CVPR 2025
LIM: Large Interpolator Model for Dynamic Reconstruction CVPR 2025
VGGSfM: Visual Geometry Grounded Deep Structure From Motion CVPR 2024
GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learning ECCV 2024
Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos ECCV 2024
Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials NIPS 2024
ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models CVPR 2024
Self-Supervised Correspondence Estimation via Multiview Registration WACV 2023
HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images CVPR 2023
Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories CVPR 2023
Replay: Multi-modal Multi-view Acted Videos for Casual Holography ICCV 2023
PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment ICCV 2023
HoloFusion: Towards Photo-realistic 3D Generative Modeling ICCV 2023
KeyTr: Keypoint Transporter for 3D Reconstruction of Deformable Objects in Videos CVPR 2022
iSDF: Real-Time Neural Signed Distance Fields for Robot Perception RSS 2022
Unsupervised Learning of 3D Object Categories From Videos in the Wild CVPR 2021
DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension ICCV 2021
Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category Reconstruction ICCV 2021
Discovering Relationships Between Object Categories via Universal Canonical Maps CVPR 2021
NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go CVPR 2021
Continuous Surface Embeddings NIPS 2020
3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data NIPS 2020
Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction NIPS 2020
PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments NIPS 2019
C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion ICCV 2019
Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels NIPS 2019
Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection CVPR 2018
Semi-convolutional Operators for Instance Segmentation ECCV 2018
AnchorNet: A Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching CVPR 2017
Learning 3D Object Categories by Looking Around Them ICCV 2017
Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection ICCV 2015