Unifying 2D and 3D Vision-Language Understanding

[AAAI 2025]Text to Point Cloud Localization with Multi-Level Negative Contrastive Learning

🔮 UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning (NeurIPS 2025)

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

[ICCV'25] 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

[CVPR 2025] 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer

[CVPR 2024] "LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning"; an interactive Large Language 3D Assistant.

[ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'

Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

😎 up-to-date & curated list of awesome 3D Visual Grounding papers, methods & resources.

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

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

[CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.

[ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Implementation for HiPrune, a training-free visual token pruning method for VLM acceleration.

[ICCV 2025] IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

The code repository of "MBQ: Modality-Balanced Quantization for Large Vision-Language Models"

[ICCV '25 Highlight] CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching

See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction

LATTICE: Scalable High-Fidelity 3D Generation via ?

[NeurIPS 2025] Completeness-Aware Reconstruction Enhancement

[ICCV25] Official code for paper “RobuSTereo: Robust Zero-Shot Stereo Matching under Adverse Weather.”

[CVPR2025] Feat2GS: Probing Visual Foundation Models with Gaussian Splatting

Official implementation of our ICCV'25 paper "Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space"

Code for RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion [3DV 2025]

[ICCV 2025] NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes