Notes
Semi-dense Visual Odometry for a Monocular Camera
A Gentle Introduction to Sheaves on Graphs
Lachha Paratha
NAAMII NeRF Paper Reading Session
RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Group (Mathematics)
Lie Groups and Lie Algebra
Rank Diminishing in Deep Neural Networks
Sheaves are the canonical datastructure for sensor integration
Bundle Adjustment
Cameras as Rays: Pose Estimation via Ray Diffusion
UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping
Denoising Diffusion Probabilistic Models
3D Gaussian Splatting as Markov Chain Monte Carlo
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views
RayZer: A Self-supervised Large View Synthesis Model
VGGT: Visual Geometry Grounded Transformer
DiffGS: Functional Gaussian Splatting Diffusion
pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction
Manifold Sampling for Differentiable Uncertainty in Radiance Fields
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction
3D Gaussian Splatting for Real-Time Radiance Field Rendering
On Incorporating Scale into Graph Networks
Expectation Maximization
PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment
SuperGlue: Learning Feature Matching with Graph Neural Networks
Mathematical Supplement for the \$\textbackslash texttt\gsplat\\$ Library
Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models
Improved Techniques for Training Score-Based Generative Models
Deep Sets
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion
Variational Auto Encoders
Interpreting and Improving Diffusion Models from an Optimization Perspective
Structured 3D Latents for Scalable and Versatile 3D Generation
Seven Sketches in Compositionality: An Invitation to Applied Category Theory
Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
Diffusion Models For Multi-Modal Generative Modeling