Junfeng Ni

MeGAS. [ECCV 2026] MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing

sam2-annotation-tools. Jupyter Notebook

DiffWind. [ICLR 2026] DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics

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

PLANING.

ShapeR. Code for the ShapeR research paper

SCaR-3D. 3D Change Detection

Depth-Anything-3. Depth Anything 3

sam-3d-objects. SAM 3D Objects

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

IGGT_official. [ICLR'26] IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction

Seed3D.

FastVGGT. [ICLR 2026] FastVGGT: Fast Visual Geometry Transformer

G4Splat. Official implementation of ICLR26 paper "G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior"

FlashWorld. Code for "FlashWorld: High-quality 3D Scene Generation within Seconds" (ICLR 2026 Oral)

HoloScene. Official Code Release of NeurIPS 2025 Paper: HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video

Orientation_Matters. Official repository for the paper "Orientation Matters: Making 3D Generative Models Orientation-Aligned" (NeurIPS 2025)

HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

MILo. [SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction

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

UnityGaussianSplatting. Toy Gaussian Splatting visualization in Unity

GSFixer. [ICML 2026] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

TexVerse. Official Repo of TexVerse: A Universe of 3D Objects with High-Resolution Textures

Amodal3R. Python

Trace3D. Official implementation of ICCV25 paper "Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing"

InteriorGS. InteriorGS: 3D Gaussian Splatting Dataset of Semantically Labeled Indoor Scenes

fuck-u-code. Legacy-Mess Detector – assess the “legacy-mess level” of your code and output a beautiful report

cog-nvs. [NeurIPS 2025] Official code for Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos

InstaScene. [ICCV 2025] InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes

SpaTrackerV2. [ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy

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

StreamVGGT. [ICLR 2026] Streaming 4D Visual Geometry Transformer

DetAny3D. [ICCV 2025] Detect Anything 3D in the Wild

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

MetaScenes. Python

LeetCUDA. LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.

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

Prior-Depth-Anything. Python

RayZer. Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"

bpy-renderer. Python package for rendering 3D scenes and animations using blender.

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

Awesome-Multimodal-Next-Token-Prediction. [Survey] Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

Awesome-3D-Scene-Generation. A curated list of awesome 3D scene generation papers. (arXiv 2505.05474)

splatt3r. Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

UniRig. [SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

ml-matrix3d. [CVPR 2025 Highlight] Matrix3D: Large Photogrammetry Model All-in-One

vlarl. Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.

HoloPart. HoloPart: Generative 3D Part Amodal Segmentation

bpt. Official code for paper: Scaling Mesh Generation via Compressive Tokenization [CVPR'25]

TrajectoryCrafter. [ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

Free360. Code for "Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views", CVPR 2025

MV-Adapter. [ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

MOVIS-render. Python

TripoSF. SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

Aether. [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling

SpatialLM. [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

TACO-code. Official implementation of ICCV 2025 paper "TACO: Taming Diffusion for in-the-wild Video Amodal Completion"

MOVIS-code. Official implementation of CVPR 2025 paper "MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes"

m3-spatial. [ICLR 2025] Official Implementation of M3: 3D-Spatial Multimodal Memory

SceneVerse. Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"

DeepMesh. [ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

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

DP-Recon. Official implementation of CVPR25 paper "Decompositional Neural Scene Reconstruction with Generative Diffusion Prior"

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

TreeMeshGPT. [CVPR 2025] TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

MIDI-3D. [CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

ManiGaussian. [ECCV 2024] ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation

guidedvd-3dgs. Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR2025 Highlight)

MAtCha. [CVPR 2025 - Spotlight] Official PyTorch implementation of MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views

PanSplat. 🍳 [CVPR'25] PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting

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

EgoLife. [CVPR 2025] EgoLife: Towards Egocentric Life Assistant

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

fast3r. [CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Dataset. News: the 10k dataset is ready for download.

SLAM3R. [CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R

ArtGS. Python

UniGS. Paper: UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting

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

Sa2VA. Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)

FDS. [ICLR 2025] Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors

awesome-blender. 🪐 A curated list of awesome Blender addons, tools, tutorials; and 3D resources for everyone.

phobos. An add-on for Blender allowing to create URDF, SDF and SMURF robot models in a WYSIWYG environment.

Long-LRM. Self-reimplemented version of Long-LRM.

nr3d_lib. Modules, operators and utilities for 3D neural rendering in single-object, multi-object, categorical and large-scale scenes.

QGS. [ICCV'25] Quadratic Gaussian Splatting: High Quality Surface Reconstruction with Second-order Geometric Primitives.

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

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

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"

CUT3R. Official implementation of Continuous 3D Perception Model with Persistent State

GaussianEditor. [CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

GS-LIVO. C++

SCube. [NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

uco3d. Uncommon Objects in 3D dataset

GameFactory. [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos

DiffGS. [NeurIPS'2024]: DiffGS: Functional Gaussian Splatting Diffusion

differentiable-rigid-body-simulator. Differentiable rigid body simulator used in PhyRecon

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

3DEnhancer. [CVPR 2025] 3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement

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.

cubvh. Mesh tools.

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

Dora. [CVPR 2025] Official repository for "Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders"

See3D. [CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

AnyBimanual. [ICCV2025] AnyBimanual: Transfering Unimanual Policy for General Bimanual Manipulation

Align3R. [CVPR 2025 Highlight] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

TEXGen. [SIGGRAPH Asia 2024, Best Paper Honorable Mention] This is the official implementation of our SIGGRAPH Asia journal artical: TEXGen: a Generative Diffusion Model for Mesh Textures

3DGS-Enhancer.

samurai. Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

autovfx. Offical codes for "AutoVFX: Physically Realistic Video Editing from Natural Language Instructions."

SlotLifter. Code for "SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields" (ECCV 2024)

YAPL. Yet another paper list on 3D vision | Robotics | Embodied AI.

GenXD. GenXD: Generating Any 3D and 4D Scenes. ICLR 2025

erasedraw-data. [ECCV 2024] Code for "EraseDraw: Learning to Insert Objects by Erasing Them from Images"

SP_GS. Superpoint Gaussians Splatting for Real-Time High-Fidelity Monocular Dynamic Scene Reconstruction

Grounded-SAM-2. Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

awesome-3DGS. 3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities

StableNormal. [SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

GSRec. :arrows_counterclockwise: [ECCV‘24] Pytorch implementation of 'Surface Reconstruction from 3D Gaussian Splatting via Local Structural Hints'

neuralangelo. Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

gaussian_surfels. [SIGGRAPH'24] Implementations for "High-quality Surface Reconstruction using Gaussian Surfels".

OpenCLAY. CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

MeshAnything. [ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

Template. Python

CraftsMan3D. CraftsMan: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner

DreamPhysics. [AAAI 2025] DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors

behavior-vision-suite.github.io. CSS

MeshXL. [NeurIPS 2024] MeshXL: Neural Coordinate Field for Generative 3D Foundation Models, a 3D fundamental model for mesh generation

Atlas3D. [NeurIPS 2024] Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication

DreamMat. [SIGGRAPH2024] DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models

project-page-template. HTML

Phobos-Motion. Use Phobos to animate robot motions in Blender.

Ag2Manip. Code Repository for "Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations"

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

PhyRecon.github.io. HTML

Awesome-Object-Compositional-INR. :book: A collection of object-compositional modeling by implicit neural representation.

dn-splatter. DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting

feature-splatting. Python

gaustudio. A Modular Framework for 3D Gaussian Splatting and Beyond

generalizing_shape_retrieval. Official Implementation of the paper "Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects", 3DV 2024

awesome-scene-understanding. 😎 A list of awesome scene understanding papers.

SDFusion. C++

GenDexGrasp. Code Repository for GenDexGrasp: Generalizing Dexterous Grasping across Robotic Hands via Contact Map Matching

scannetpp. [ICCV 2023 Oral] ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

Simulately. A universal summary of current robotics simulators

DebSDF. [TPAMI 2024] DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction

SSR-code. Official implementation of 3DV24 paper "Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture"

Junfeng-Ni. Welcome to my homepage!

SSR. CSS

3D-Tools. Python

RICO. :couch_and_lamp: [ICCV2023] RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction

stannum. Fusing Taichi into PyTorch

taichi. Productive, portable, and performant GPU programming in Python.

model-viewer. Easily display interactive 3D models on the web and in AR!

point_transformer.scannet. point transformer pre-trained on scannet

learning_research. 本人的科研经验

BO-QSA. This repository is the official implementation of Improving Object-centric Learning With Query Optimization

infinigen. Infinite Photorealistic Worlds using Procedural Generation

prolificdreamer. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

self6dpp. Self6D++: Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2024.

GET3D. Python

PartManip. [CVPR 2023] PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations

GAPartNet. [CVPR 2023 Highlight] GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts.

shap-e. Generate 3D objects conditioned on text or images

kit. 🧱 Describe your site, AI builds it, you own it as Markdown. Snap together Tailwind blocks like Lego — landing pages, blogs, portfolios, docs & more. No AI slop. Free to deploy anywhere 👇

nvitop. An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

chatGPTBox. Integrating ChatGPT into your browser deeply, everything you need is here

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

HashNeRF-pytorch. Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/

gdrnpp_bop2022. [T-PAMI'25] PyTorch Implementation of GDRNPP, winner (most of the awards) of the BOP Challenge 2022 at ECCV'22

Replica-Dataset. The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

InstPIFu. repository of "Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes" ECCV2022

habitat-sim. A flexible, high-performance 3D simulator for Embodied AI research.

deep-learning-for-image-processing. deep learning for image processing including classification and object-detection etc.

OpenPCDet-Noted. OpenPCDet代码分析与注释