Fangjinhua Wang

img2threejs. Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

Awesome-Interactive-World-Model. A Comprehensive Survey of Interactive Video World Models

STEM2M. Morphology prediction of small nanoparticles from single HAADF-STEM images

OSI-Bench. Official repo of From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs

DepthLM_Official. [ICLR 2026 Oral (top 1.2%)] Official implementation of DepthLM

diffmvs. [T-PAMI 2025] DiffMVS & CasDiffMVS

nwm. Official code for the CVPR 2025 paper "Navigation World Models".

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

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

Pyramid-Flow. [ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

scrstudio. [CVPR 2025] A unified framework for Scene Coordinate Regression-based visual localization

HSR. HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos (ECCV 2024)

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

depthsplat. [CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

openvla. OpenVLA: An open-source vision-language-action model for robotic manipulation.

dust3r. DUSt3R: Geometric 3D Vision Made Easy

mast3r. Grounding Image Matching in 3D with MASt3R

Pandora. Pandora: Towards General World Model with Natural Language Actions and Video States

glace. [CVPR 2024] GLACE: Global Local Accelerated Coordinate Encoding

home-robot. Mobile manipulation research tools for roboticists

open_clip. An open source implementation of CLIP.

Awesome-LLM-Robotics. A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

deep-video-mvs. Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)

AdaBins. Official implementation of Adabins: Depth Estimation using adaptive bins

VolRecon. Official code of VolRecon (CVPR 2023)

IterMVS. Official code of IterMVS (CVPR 2022)

StableViewSynthesis. Python

MiDaS. Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

PatchmatchNet. Official code of PatchmatchNet (CVPR 2021 Oral)