Jianyuan Wang

16

Papers

327

Total Citations

Papers (16)

CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos

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

AutoPartGen: Autoregressive 3D Part Generation and Discovery

UnCommon Objects in 3D

Unlocking the Potential of Reverse Distillation for Anomaly Detection

Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes

Deep Two-View Structure-From-Motion Revisited

Improving GAN Equilibrium by Raising Spatial Awareness

Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning

PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

Audio—Visual Segmentation

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

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

VGGT: Visual Geometry Grounded Transformer

SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation