ICLR 2022 accepted papers on 3D vision
17 of the 1,095 papers accepted at ICLR 2022 (1.6%) are on 3D vision, compared with 1.2% at ICLR 2021. They fall into 5 topics.
See ICLR 2022 in the interactive map
Submitting to ICLR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Face and shape · 7 papers
- Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields (23 citations)
- CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture (8 citations)
- RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation (4 citations)
- Probabilistic Implicit Scene Completion (2 citations)
- Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization (1 citation)
- Adaptive Wavelet Transformer Network for 3D Shape Representation Learning
- Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image
3D generation · 4 papers
- VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects (25 citations)
- Learning Continuous Environment Fields via Implicit Functions (5 citations)
- IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes (2 citations)
- An Autoregressive Flow Model for 3D Molecular Geometry Generation from Scratch
Depth and stereo · 2 papers
- CURVATURE-GUIDED DYNAMIC SCALE NETWORKS FOR MULTI-VIEW STEREO (21 citations)
- Visual Correspondence Hallucination (5 citations)
