liuyuan-pal

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

mamba

Mamba SSM architecture

dust3r

DUSt3R: Geometric 3D Vision Made Easy

TripoSR

champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Marigold

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

4D-Humans

4DHumans: Reconstructing and Tracking Humans with Transformers

FoundationPose

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

MonoGS

[CVPR'24 Highlight] Gaussian Splatting SLAM

SMPLer-X

Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"

GaussianObject

Code for "GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting"

pixelsplat

[CVPR 2024 Oral] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, and Vincent Sitzmann

GeoWizard

[arXiv'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

Octree-GS

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

NVDS

The official repository of the ICCV2023 paper "Neural Video Depth Stabilizer" (NVDS).

V3D

V3D: Video Diffusion Models are Effective 3D Generators

GaussianAvatar

[CVPR 2024] The official repo for "GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians"

MOSE-api

[ICCV 2023] MOSE: A New Dataset for Video Object Segmentation in Complex Scenes

deep-image-matching

Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM software. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.

robust_cvd

Robust Consistent Video Depth Estimation

Consistent4D

[ICLR 2024] Official Implementation of Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video

LL3DA

[CVPR 2024] "LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning"; an interactive Large Language 3D Assistant.

InTeX

Interactive Text-to-Texture Synthesis via Unified Depth-aware Inpainting.

SemCity

[CVPR 2024] The official implementation for "SemCity: Semantic Scene Generation with Triplane Diffusion"

SceneScape

Official Pytorch Implementation for "SceneScape: Text-Driven Consistent Scene Generation"

SuperNormal

[CVPR 2024] Official implementation of "SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration"

mvdfusion

[CVPR 2024] MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

objaverse_filter

naive filter of objaverse

ThemeStation