Stars
MegaFlow: Zero-Shot Large Displacement Optical Flow
[NeurIPS 2025] Pixel-Perfect Depth
[ICLR'26] YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
A pipeline parallel training script for diffusion models.
[NeurIPS'25] A work to improve CLIP's visual detail capturing ability by inverting the unCLIP generative model.
The official implementation of CVPR Workshop 2025 paper: Window Token Concatenation for Efficient Visual Large Language Models.
This repository collects papers on VLLM applications. We will update new papers irregularly.
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling
[TIP 2026] ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
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 th…
[DEPRECATED] GLOMAP - Global Structured-from-Motion Revisited
CUDA accelerated rasterization of gaussian splatting
[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacch…
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.
An open-source impl. of Large Reconstruction Models
Generative Models by Stability AI
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
[CVPR'23] Self-Supervised Super-Plane for Neural 3D Reconstruction
Replace the shit💩 new feed with the old one.
EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
A diffuser implementation of Zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV23)
[ECCV 2022] Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
The official implementation of CVPR2023 paper "DISC: Learning from Noisy Labels via Dynamic Instance-Specific Selection and Correction"
A unified framework for 3D content generation.