Linus Härenstam-Nielsen

ShapeR. Code for the ShapeR research paper

Video-Depth-Anything. [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Sparse2DGS. [CVPR2025]

buildbpy. a better builder for Blender as a Python module (bpy)

lingbot-world. Advancing Open-source World Models

TripoSplat. TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.

Voxurf. [ ICLR 2023 Spotlight ] Pytorch implementation for "Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction"

amazon-berkeley-objects. Python

superpowers. An agentic skills framework & software development methodology that works.

GenRecon. Python

world-tracing. Office inference code for World Tracing (object/scene/dynamic). Live demos: https://haoz19.github.io/world-tracing-page/

recgen. Jupyter Notebook

minit2i-torch. Official PyTorch re-implementation of MiniT2I.

meshflow. Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan and Andrea Vedaldi.

V2M4. A novel 4D reconstruction method that directly generates high-quality, animation-ready 4D mesh asset (.GLB file) from a single monocular video.

learning-convex-decomposition. Python

echoscene. [ECCV 2024] EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion.

Open-d4rt. Python

odysseus. Self-hosted AI workspace.

CertifiableFactors. Code of the paper "Simplifying Certifiable Estimation: A Factor Graph Optimization Approach"

LAMP. [CVPR 26'] Code for the LAMP research paper.

FigMirror. An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.

unidiffuser. Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"

NATTEN. Fast Multi-dimensional Sparse Attention

Pixal3D. [SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

vggt-omega. [CVPR 2026 Oral] VGGT Omega

image-blaster. An image-to-world skillset for Claude.

egoflow. Python

ELF. Python

EscherNet. [CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis

LoGeR. Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

NPC. [ICLR 2026] Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning.

HY-SOAR. HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models

lingbot-map. A feed-forward 3D foundation model for reconstructing scenes from streaming data

AniGen. [SIGGRAPH 2026] AniGen: Unified S^3 Fields for Animatable 3D Asset Generation

ai4animationpy. A Python framework for AI-driven character animation using neural networks.

nova3r. [ICLR 2026] NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction

SGPnP. Python

LoMa. [ECCV 2026 Oral] LoMa: Local Feature Matching Revisited

paper2code. Agent skill to turn any arxiv paper into a working implementation

Awesome-Latent-Space. A paper list of Awesome Latent Space.

loss-landscape. Code for visualizing the loss landscape of neural nets

resplat. [ECCV'26 Oral] ReSplat: Learning Recurrent Gaussian Splatting

gg-langevin. Jupyter Notebook

DROID-W. [CVPR 2026] DROID-SLAM in the Wild

MV-SAM3D. SAM 3D Objects with Multi-view Images

worldfm. Python

super_primitive. [CVPR'24, Demo Track Honourable Mention] SuperPrimitive: Scene Reconstruction at a Primitive Level

DKT. [ICRA2026] official implement of "Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation"

DrivIng. Python

BiFlow. Official Implementation of BiFlow https://arxiv.org/abs/2512.10953

DiffusionGeometry. The code for "Computing Diffusion Geometry" (2026).

RaCo. Ranking and Covariances for Practical Learned Keypoints

Awesome-Global-Solvers-for-3D-Vision. A curated survey and paper list for global solvers in 3D vision: certifiable optimization, convex relaxation, Branch-and-Bound, and robust estimation.

faster-gaussian-splatting. An efficient and research-friendly Gaussian Splatting framework described in the CVPR'26 paper "Faster-GS: Analyzing and Improving Gaussian Splatting Optimization"

lm-rs. Python

multi-view-sam-3d-objects. SAM 3D Objects with Multi Images

imeanflow. Official Implementation of iMF https://arxiv.org/abs/2512.02012

meanflow. JAX implementation of MeanFlow

InstantMesh. InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

ComfyUI-Hunyuan3DWrapper. Python

TTM. Official Pytorch Implementation for "Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising"

blender-mcp. Open-source MCP to use Blender with any LLM

trustcall. Tenacious tool calling built on LangGraph

nodebpy. Build node trees in Blender more elegantly with code

DPHM. [CVPR2024] DPHMs: Diffusion Parametric Head Models for Depth-based Tracking

jvp_flash_attention. Flash Attention Triton kernel with support for second-order derivatives

sdf-dataset. Port of the Takikawa conservative SDF dataset to C++

MeshRipple. [CVPR 2026 highlight!] MeshRipple: Structured Autoregressive Generation of Artist-Meshes

TRELLIS.2. Native and Compact Structured Latents for 3D Generation

navi. Jupyter Notebook

banana-slides. 一个基于nano banana pro🍌的原生AI PPT生成应用，迈向＂Vibe PPT＂; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌

GuideFlow3D. [NeurIPS 2025] GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer

RobustVGGT. [CVPR'26] Official implementation of "Emergent Outlier View Rejection in Visual Geometry Grounded Transformers"

gpytoolbox. A collection of utility functions to prototype geometry processing research in python

mesh_to_sdf. Calculate signed distance fields for arbitrary meshes

pymeshfix. Python Wrapper for MeshFix: easily repair holes in surface meshes

sam-3d-objects. SAM 3D Objects

RoMaV2. Python

qpax. Differentiable QP solver in JAX

batrack. [ICCV 2025 Oral] Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction (BA-Track)

UniLat3D. UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation

EqM. Python

lamaria. Benchmarking Visual-Inertial SLAM at City Scale (ICCV 2025).

TTT3R. [ICLR 2026] A simple state update rule to enhance length generalization for CUT3R

FLAIR. Python

slam-handbook-public-release. Release repo for our SLAM Handbook

met3r. [CVPR '25] MEt3R: Measuring Multi-View Consistency in Generated Images

geco. Jupyter Notebook

dspy. DSPy: The framework for programming—not prompting—language models

flowseek. Source code for ICCV 2025 paper "FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases"

blender-plots. Python library for making 3D plots with blender

GeodesicDiffusion. Offical implementation for "Probability Density Geodesics in Image Diffusion Latent Space" (CVPR2025)

SkeletonDiffusion. Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction: SkeletonDiffusion, a latent diffusion model with attention graph architecture

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

gtsfm. End-to-end SFM framework based on GTSAM

signed-heat-3d. C++ library implementing the Signed Heat Method for computing robust signed distance fields (SDFs) to triangle meshes, polygon meshes, and point clouds in 3D.

GeoSPSR. Python

repulsive-shells. C++

LongSplat. [ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

HunyuanWorld-1.0. Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

1-Lipschitz-Neural-Distance-Fields. Signed distance field computation using 1-Lipschitz neural networks - Pytorch implementation

awesome-jax. JAX - A curated list of resources https://github.com/google/jax

flow. Python

rembg. Rembg is a tool to remove images background

LaGeM. Python

fairscale. PyTorch extensions for high performance and large scale training.

Pi3. [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning

stochastic-preconditioning. Python

HotSpot. Python

distortion_averaging. PRaDA: Projective Radial Distortion Averaging

XM-code. Code for our paper "Building Rome with Convex Optimization".

VecSetX. Python

SDFusion. C++

RLfinetuning_Diffusion_Bioseq. Code for the tutorial/review paper for RL-based-fine-tuniing. In this code, we especially focus on the design of biological sequences like DNA (enhancers) and RNA (UTRs) design.

TripoSG. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

SemLA. [CVPR'25] Official implementation of "Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation"

shape-completion. 3D Shape Completion - adaptation and improvement of DiffComplete model.

DiffComplete. Official Codebase of "DiffComplete: Diffusion-based Generative 3D Shape Completion"

sonata. [CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations

AnyCalib. AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025)

stable-virtual-camera. Stable Virtual Camera: Generative View Synthesis with Diffusion Models

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

open-oasis. Inference script for Oasis 500M

anycam. Official repository for "AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos" (CVPR 2025)

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

WoodScape. The repository containing tools and information about the WoodScape dataset.

splat. WebGL 3D Gaussian Splat Viewer

svraster. [CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

PIN_SLAM. 📍PIN-SLAM: LiDAR SLAM Using a Point-Based Implicit Neural Representation for Achieving Global Map Consistency [TRO 24]

stable-point-aware-3d. SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

Implicit-surf-Deformation. code for Implicit Neural Surface Deformation with Explicit Velocity Fields (ICLR2025)

DeepSeek-R1.

3DShape2VecSet. Python

NoPoSplat. [ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

colmap_cameras_pytorch. Colmap camera models implemented in PyTorch

GeoCalib. GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

monst3r. Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

st-2dgs.

ifusion. [3DV 2025] iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views

rd. [ECCVW 2024] Are Minimal Radial Distortion Solvers Necessary for Relative Pose Estimation?

3DGS-LM. 3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt. (ICCV 2025)

slang-gaussian-rasterization. Slang

spann3r. [3DV'25 Award Candidate] 3D Reconstruction with Spatial Memory

ViewCrafter. [TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis

threestudio. A unified framework for 3D content generation.

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

sjc. Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation (CVPR 2023)

ZoeDepth. Metric depth estimation from a single image

genwarp. Python

mini-dust3r. Python

Universal-Guided-Diffusion. Jupyter Notebook

splatviz. Full python interactive 3D Gaussian Splatting viewer for real-time editing and analyzing.

tapnet. Tracking Any Point (TAP)

mast3r. Grounding Image Matching in 3D with MASt3R

implicit_dist. C++

radialsfm. 1D Radial Structure-from-Motion (Larsson et al., ECCV 2020)

taming-3dgs. Python

dataset.

3dgs-mcmc. [NeurIPS 2024 Spotlight] Implementation of the paper "3D Gaussian Splatting as Markov Chain Monte Carlo"

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Deblur-GS. [I3D 2024] Deblur-GS: 3D Gaussian Splatting from Camera Motion Blurred Images

Photo-SLAM. [CVPR 2024] Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras

blender_mathematics. short python scripts

jaxsplat. 3D Gaussian Splatting in JAX

diff-gaussian-rasterization-for-gsslam. The modified differential Gaussian rasterization in the CVPR 2024 highlight paper: GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting.

point-radiance. [SIGGRAPH Asia 2022] Differentiable Point-Based Radiance Fields for Efficient View Synthesis

iComMa. iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching

model-explorer. A modern model graph visualizer and debugger

PatchDropout. Python

croco. Python

awesome-dust3r. 🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.

GSDF. [NeurIPS 2024]GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction

camp_zipnerf. Python

ges-splatting. Original reference implementation of "GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering" [CVPR 2024]

awesome-3D-gaussian-splatting. Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

gaussian-splatting-blender-addon. Python

GCNv2_SLAM. Real-time SLAM system with deep features

como. [ECCV 2024 Oral] COMO: Compact Mapping and Odometry

Hierarchical-Localization. Visual localization made easy with hloc

splatter-image. Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024

gsplat. CUDA accelerated rasterization of gaussian splatting

sdf-edit-rs. Rust

LichtFeld-Studio. Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

diff-gaussian-rasterization. Cuda

diff-gaussian-rasterization-w-pose. Cuda

neurad-studio. [CVPR2024] NeuRAD: Neural Rendering for Autonomous Driving

SplaTAM. SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)

MonoGS. [CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM

DSINE. [CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

dust3r. DUSt3R: Geometric 3D Vision Made Easy

SuGaR. [CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

points2surf. Learning Implicit Surfaces from Point Clouds (ECCV 2020)

tabilize. Simple code for generating a color-coded latex table from raw data

Neural-Singular-Hessian. Code of Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian. ACM Transactions on Graphics (SIGGRAPH Asia 2023).

POCO. [CVPR 2022] POCO: Point Convolution for Surface Reconstruction

BlenderDataVis. Data visualisation addon for Blender

NeuralPull-Pytorch. Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

NeuralPull. Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces