Wan: Open and Advanced Large-Scale Video Generative Models

Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)

[ICCV 2025] SuperDec: 3D Scene Decomposition with 
Superquadric Primitives.

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

[ICCV 2025] RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenes

😎 A curated list of ICCV 2025 Oral paper. In Progress

[ICCV 2025 Oral] SceneSplat - Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining

Collection of advice for prospective and current PhD students

[ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes

[ICCV2025] Official repository of the paper "Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation"

[CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

The official implementation of SAGS (Segment Anything in 3D Gaussians)

We extend Segment Anything to 3D perception by combining it with VoxelNeXt.

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

[NeurIPS 2025] Streaming 3D Reconstruction with Explicit Spatial Pointer Memory

[ICLR2025] A PyTorch implementation for STORM: Spatiotemporal Reconstruction Model for Large-Scale Outdoor Scenes

Code for FastVGGT: Training-Free Acceleration of Visual Geometry Transformer

[ICLR 2025] Point-SAM: Promptable 3D Segmentation Model for Point Clouds

[ICLR 2025] 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting

High-quality and editable surfel 3D Gaussian generation through native 3D diffusion (ICLR 2025)

[ICLR' 25] SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

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

[ICCV 2023] SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection

CVPRW 2025 (T4V)

[WACV2025] AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2

Acceptance rates for the major AI conferences

DUSt3R: Geometric 3D Vision Made Easy

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.