eccv2026 开源项目推荐（57 个）

amusi /ECCV2026-Papers-with-Code

ECCV 2026 论文和开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2026论文和开源项目

Kobaayyy /Awesome-ECCV2026-ECCV2024-ECCV2020-Low-Level-Vision

ECCV2026/ECCV2024/ECCV2020 低层视觉的论文与代码合集

TencentARC /Track4World

[ECCV 2026] Track4World：面向世界中心的全像素前馈稠密 3D 跟踪

zju3dv /habitat-gs

[ECCV 2026] Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting

zylwithxy /HRDiT

[ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models"

Allenxinn /AgentVLN

[ECCV 2026] Official code repository for : "AgentVLN: Towards Agentic Vision-and-Language Navigation"

ghanning /PolyLayout

PolyLayout: Multi-room Manhattan Layout Estimation (ECCV 2026)

JiazheWei /PosterCopilot

Official implementation for PosterCopilot

LSXI7 /Wat3R

[ECCV 2026 Oral] Wat3R: Underwater 3D Geometry Learning without Annotations

Intellindust-AI-Lab /SKEL-CF

[ECCV 2026] Pytorch implementation of "SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery"

JIA-Lab-research /RePlan

(ECCV2026) RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing

WangYuLin-SEU /WAPR

[ECCV 2026] Wide-angle pose refinement for unseen objects from RGB-D, camera intrinsics, a metric mesh, and a mask or box.

YoungRaeKimm /MemRoPE

[ECCV 2026] Official implementation of "MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens"

mlvlab /F4Splat

Official Implementation of "F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting", ECCV 2026

ShenZheng2000 /WarpI2I

[ECCV 2026] WarpI2I: Image Warping for Image-to-Image Translation.

Xiaohao-Xu /Ambiguity-in-Space

[ECCV 2026 Spotlight Oral] One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models (Layered 3D Spatial Understanding)

chenhaoqcdyq /BeyondTimeShifts

Beyond Time Shifts (ECCV 2026): a reference-free audio-visual synchronization evaluator built on Qwen2.5-Omni-3B, with SynthSync data, R-GRPO training, and the SyncBench benchmark.

irajisamurai /2D-Motion-Interface

Plug-and-play 2D motion interface for real-world Motion Language Models

ptrvilya /echo

[ECCV'26] Method for reconstructing HOI from sparse ego-centric tracking

seunghyuns98 /TriMotion

[ECCV 2026] TriMotion: Modality-Agnostic Camera Control for Video Generation