← authors · overview

• Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
  2020 · 145 citations
• Text2LIVE: Text-Driven Layered Image and Video Editing
  2022 · 27 citations
• SceneScape: Text-Driven Consistent Scene Generation
  2023 · 24 citations
• Resultant Based Incremental Recovery of Camera Pose from Pairwise Matches
  2019 · 15 citations
• Point-Cloud Completion with Pretrained Text-to-image Diffusion Models
  2023 · 5 citations
• RESfM: Robust Deep Equivariant Structure from Motion
  2024 · 1 citations
• Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
  2026
• Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation
  2026
• Neural Congealing: Aligning Images to a Joint Semantic Atlas
  2023
• Fast Encoder-Based 3D from Casual Videos via Point Track Processing
  2024
• Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors
  2024