Berna Kabadayı

DynHair. Head Avatars with Dynamic Explicit Hair [ECCV 2026]

GNM. An open ecosystem of parametric human models and perception stacks, starting with GNM Head.

NeuralFur. NeuralFur: Animal Fur Reconstruction From Multi-View Images [3DV 2026]

anyup. [ICLR '26 Oral] Official repository of the paper "AnyUp: Universal Feature Upsampling".

AnimateDiff. Official implementation of AnimateDiff.

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

hallo. Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

nglod. Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes (CVPR 2021 Oral)

InST. Official implementation of the paper “Inversion-Based Style Transfer with Diffusion Models” (CVPR 2023)

ComfyUI-TeleStyle. Python

TeleStyle. state-of-the-art content-preserving style transfer

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

DiffSynth-Studio. Enjoy the magic of Diffusion models!

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

DAMA-code. [PhysHuman @ CVPR2026] DAMA: Disentangled Body-Anchored Gaussians for Controllable Multi-Layered Avatars

MultiTalk. [NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

Qwen3-Omni. Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

confingy. An implicit configuration system for Python

ml-lito. [ICLR 2026] LiTo: Surface Light Field Tokenization

dotfiles. Shell

LVSM. [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"

recastnavigation. Industry-standard navigation-mesh toolset for games

Depth-Anything-3. Depth Anything 3

genwarp. Python

FramePack. Lets make video diffusion practical!

croco. Python

LEXIS. [arXiv 2026] LEXIS: LatEnt ProXimal Interaction Signatures for 3D HOI from an Image

claude-hud. A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress

octformer. OctFormer: Octree-based Transformers for 3D Point Clouds [SIGGRAPH 2023]

HY-World-2.0. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

lyra. Project Lyra: Open Generative 3D World Models

SpeechDrivenTongueAnimation. ML-driven tongue animation (CVPR'22)

lagernvs. Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

autoresearch. AI agents running research on single-GPU nanochat training automatically

personaplex. PersonaPlex code.

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

tongue. We propose a framework that accurately derives the 3D tongue shape from single images. A high detailed 3D point cloud of the tongue surface and a full head topology along with the tongue expression can be estimated from the image domain.

physhead. [CVPR 2026] PhysHead: Simulation-Ready Gaussian Head Avatars

LitePT. [CVPR 2026 Highlight] LitePT: Lighter Yet Stronger Point Transformer

nerfify-code. [CVPR 2026 Highlight] Offical code for- NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code

DMM. An Implicit Parametric Morphable Dental Model

pixie. Feed-forward model for predicting 3D physics with 3DGS + NeRF

meshgraphnets. Rewrite deepmind/meshgraphnets into pytorch

nerfbaselines. Reproducible evaluation of NeRF and 3DGS methods

3DGen-Playground. 3D generation made easy!

large-steps-pytorch. Implementation of "Large Steps in Inverse Rendering of Geometry"

NeMO. Official Repository for "Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception"

research-skills. Claude Code skills for AI/ML researchers

tofu. Official code for ICCV 2021 oral paper: Topologically Consistent Multi-View Face Inference Using Volumetric Sampling

CARI4D. [CVPR 2026] CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction

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

DreamDojo. Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)

awesome-vlm-architectures. Famous Vision Language Models and Their Architectures

SenseNova-SI. [CVPR 2026] Scaling Spatial Intelligence with Multimodal Foundation Models

infinigen. Infinite Photorealistic Worlds using Procedural Generation

MoLingo. [ CVPR 2026 ] MoLingo: Motion-Language Alignment for Text-to-Motion Generation

stable-worldmodel. A platform for reproducible world model research and evaluation

LTX-Video. Official repository for LTX-Video

FastGen. NVIDIA FastGen: Fast Generation from Diffusion Models

spear. SPEAR: A Simulator for Photorealistic Embodied AI Research

cookbook. Examples and guides for using the Gemini API

kauldron. Modular, scalable library to train ML models

SO-ARM100. Standard Open Arm 100

DiSECt. Differentiable Cutting Simulator

cosmos-predict2.5. Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

LongLive. Long Video Gen Infrastructure

gemma. Gemma open-weight LLM library, from Google DeepMind

pixel3dmm. [Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction

IsaacLab. Unified framework for robot learning built on NVIDIA Isaac Sim

nexels. The official repository for Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries

UniAnimate-DiT. UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer

mesh-splatting. Python

cwm. Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

MPMAvatar. MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025)

TensorRT-LLM. TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

AniMer. AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer (CVPR2025)

DoRA. [SIGGRAPH 2025 (Journal Track)] Facial Appearance Capture at Home with Patch-Level Reflectance Prior.

densemarks. [ICLR 2026] DenseMarks: dense per-pixel embeddings replacing standard face landmarks

FaceOLAT. Repository for Dataprocessing of FaceOLAT Dataset

beta-splatting. [SIGGRAPH'25] Official implementation for the paper "Deformable Beta Splatting"

tridi. [ICCV'25] Method for generating static human-object interactions

mujoco_warp. GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.

newton. An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

InfiniHuman. [SIGGRAPHASIA2025] InfiniHuman: Infinite 3D Human Creation with Precise Control

Phy-SIC. [SIGGGRAPHASIA2025] PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image

BEHAVIOR-1K. BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx

text-to-text-transfer-transformer. Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

viser. Web-based 3D visualization in Python

IntrinsiX. IntrinsiX: High-Quality PBR Generation using Image Priors

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

VILA. VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

spark. :sparkles: An advanced 3D Gaussian Splatting renderer for THREE.js

rapier. 2D and 3D physics engines focused on performance.

MoGe. [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

map-anything. MapAnything: Universal Feed-Forward Metric 3D Reconstruction

mega-sam. Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

Im2Haircut. Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars [ICCV 2025]

GEN3C. [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

animal_papers. Awesome papers for markerless animal motion capture and 3D reconstruction.

ollama. Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

DAViD. Python

HyperGaussians. HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars

awesome-neural-physics. TeX

posescript. Code for the PoseScript (ECCV 22) and PoseFix (ICCV 23) papers.

OmniAvatar. Python

laplacian_blend. Tutorial on Laplacian Image Blending

PhysRig. Physics-based rigging with MPM for realistic character animation. ICCV 2025.

metaquery. Official Implementation of Paper Transfer between Modalities with MetaQueries

diffusion-posterior-sampling. Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"

OmniGen2. OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

vggt-blender. Blender addon for vggt 3D reconstruction

3dgrut. Ray tracing and hybrid rasterization of Gaussian particles

gen-omnimatte-public. Generative Omnimatte (CVPR 2025)

Go-with-the-Flow. The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"

Hunyuan3D-2.1. From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

HOIDiNi. Python

cosmos-transfer1-diffusion-renderer. Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework

awesome-llm-apps. 100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.

NeuralHaircut. Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction. ICCV 2023

SMPLSim. Simulating SMPL humanoid, supporting PHC/PHC-MJX/PULSE/SimXR code bases.

spiritlm. Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".

WorldGen. 🌍 WorldGen - Generate Any 3D Scene in Seconds

InterMimic. [CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions

labelme. Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.

smalst. Python

DecoupledGaussian. Jupyter Notebook

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

difflocks. Code for our CVPR'25 paper - "DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models"

FloED-main. Coherent Video Inpainting Using Optical Flow-Guided Efficient Diffusion

LoRA. Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

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

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

SMALify. This repository contains an implementation for performing 3D animal (quadruped) reconstruction from a monocular image or video. The system adapts the pose (limb positions) and shape (animal type/height/weight) parameters for the SMAL deformable quadruped model, as well as camera parameters until the projected SMAL model aligns with 2D keypoints and silhouette segmentations extracted from the input frame(s).

BitNet. Official inference framework for 1-bit LLMs

Difix3D. [CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

POCO. [3DV 2024] POCO: 3D Pose and Shape Estimation using Confidence

InteractVLM. [CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models

FRESA. [CVPR 2025 Highlight] FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images

cosmos-predict1. Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

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

cube. Roblox Foundation Model for 3D Intelligence

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

GEM. GEM - Gaussian Eigen Models for Human Heads [CVPR 2025]

molecular-plus. particle solver for Blender 4.2+ / 5.1+

radfoam. Original implementation of "Radiant Foam: Real-Time Differentiable Ray Tracing"

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

cursor.

dust3r. DUSt3R: Geometric 3D Vision Made Easy

GRM. Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

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

MASt3R-SLAM. [CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

TransformerEngine. A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

GSOPs. Gaussian Splatting Operators for SideFX Houdini

nersemble-data. Python

goku. [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

RTXMG. NVIDIA RTX Mega Geometry SDK

oumi. Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!

TripoSR. TripoSR: Fast 3D Object Reconstruction from a Single Image

joker. Official Code Base of the Paper: "Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions"

headcraft. HeadCraft (3DV 2025)

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

PhysAvatar. Official repo for PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations, ECCV 2024

ml-hugs. Official repository of HUGS: Human Gaussian Splats (CVPR 2024)

FORCE_dataset. Dataset for FORCE - Physics-aware Human-object Interaction (3DV 2025)

CameraHMR. Python

flowface. Repository for the paper "3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow", CVPR 2024

ava-256. Train universal codec avatars

PhyRecon. Official implementation of NeurIPS24 paper "PhyRecon: Physically Plausible Neural Scene Reconstruction"

nvdiffrec. Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

smplfitter. The Fast Way From Vertices to Parametric 3D Humans

tungsten. High performance physically based renderer in C++11

Gen3Diffusion. [T-PAMI2025] Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergy

repulsive-shells. C++

gghead. [SIGGRAPH ASIA '24] GGHead: Fast and Generalizable 3D Gaussian Heads

DRTK. Differentiable Rendering Toolkit

Regional-Prompting-FLUX. Training-free Regional Prompting for Diffusion Transformers 🔥

VHAP. A complete head tracking pipeline from videos to NeRF/3DGS-ready datasets.

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

hitchhiking-rotations. Learning with 3D rotations, a hitchhiker’s guide to SO(3) - ICML 2024

diffusion-e2e-ft. [WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

SynthMoCap. SynthMoCap Datasets

nvTorchCam. Python

voxel-challenge. Python

taichi-splatting. Python

RADIO. Official repository for "AM-RADIO: Reduce All Domains Into One"

perm. [ICLR 2025] Official implementation of "Perm: A Parametric Representation for Multi-Style 3D Hair Modeling"

motionfix. MotionFix: Text-Driven 3D Human Motion Editing [SIGGRAPH ASIA 2024]

HAAR. HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles (CVPR 2024)

foundpose. FoundPose: Unseen Object Pose Estimation with Foundation Features, ECCV 2024

3dgs-render-blender-addon. 3DGS Render by KIRI Engine

GaussianHaircut. Gaussian Haircut: Human Hair Reconstruction with Strand-Aligned 3D Gaussians

GPU-Puzzles. Solve puzzles. Learn CUDA.

Frosting. [ECCV 2024 - ORAL] Official PyTorch implementation of Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering

theseus. A library for differentiable nonlinear optimization

slang-gaussian-rasterization. Slang

PuzzleAvatar. [SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums