This is a list of relevant papers for 3D Geometric Foundation Models and Applications.

Implementation of the DINOv2 perceptual loss from the PercHead paper [CVPR '26]

SAM2 as a perceptual loss

HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image (CVPR 2026 Highlight)

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

[CVPR '26] FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision

Official Implementation of the Paper:Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models (Siggraph 2025)

Official Implementation of the Paper: EchoAvatar: Real-time Generative Avatar Animation from Audio Streams (Siggraph 2026)

Grid-Free Monte Carlo Solvers for Physics Simulations Involving Partial Differential Equations

[ICLR 22, TPAMI 24] LIA: Latent Image Animator

Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".

For CVPR26 pub open source of Skullptor

The implementation of GES (When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering)

Official implementation of Gaussian point splatting (SIGGRAPH'26)

Official Pytorch Code of the Paper "FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization"

[CVPR 2026 Oral] VGGT Omega

Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr0…

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

[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

Cuda-Based Software Rasterization for Billions of Triangles

[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

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

ReSplat: Learning Recurrent Gaussian Splatting

Monocular whole-body 3D human pose estimation using the SOMA body model

Code of Strips as Tokens: Artist Mesh Generation with Native UV Segmentation. ACM Transactions on Graphics (SIGGRAPH 2026)

Implementation of Fast Weight Attention

Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.