论文阅读清单-视觉

Wed Oct 30 2024

1 分钟

126 字

Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors https://wangrc.site/Diff3DEdit/

DreamCraft3D++: Efficient Hierarchical 3D Generation with Multi-Plane Reconstruction Model https://dreamcraft3dplus.github.io/

Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats https://arthurhero.github.io/projects/llrm/

LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images https://arxiv.org/pdf/2410.15636

Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs https://splatt3r.active.vision/

StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal https://stable-x.github.io/StableNormal/

LargeSpatialModel: End-to-end Unposed Images to Semantic 3D https://largespatialmodel.github.io/

CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes https://dekuliutesla.github.io/CityGaussianV2/static/paper/CityGaussianV2.pdf鉴定Geometrically Accurate

Optical Flow Representation Alignment Mamba Diffusion Model for Medical Video Generation https://arxiv.org/abs/2411.01647Medical Video Generation

GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes https://arxiv.org/abs/2411.01853表面重建方法

SplatFormer: https://github.com/ChenYutongTHU/SplatFormerGS+Transformer，解决NVS视角与训练集分布不一致

Simanything.