scene-understanding - GitHub 开源项目专题

1

basilevh/gcd

Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation

Python ⭐ 291 ⑂ 10 GPL-3.0 · 2025-11-19推送

3d computer-vision

2025-11-19

最近推送

2

worldbench/WorldLens

[CVPR 2026 Oral] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

Python ⭐ 244 ⑂ 20 Apache-2.0 · 2026-01-18推送

3d aigc

2026-01-18

最近推送

3

worldbench/LiDARCrafter

[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

Python ⭐ 202 ⑂ 14 MIT · 2025-12-12推送

aigc autonomous-driving

2025-12-12

最近推送

4

isLinXu/paper-list

autoupdate paper list

Python ⭐ 152 ⑂ 17 Apache-2.0 · 22 小时前推送

anomaly-detection audio-processing

22 小时前

最近推送

5

ymxlzgy/echoscene

[ECCV 2024] EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion.

Python ⭐ 103 ⑂ 7 · 2024-06-04推送

diffusion-models generative-ai

2024-06-04

最近推送

6

jhcho99/CoFormer

[CVPR'22] Official PyTorch Implementation of "Collaborative Transformers for Grounded Situation Recognition"

Python ⭐ 51 ⑂ 7 Apache-2.0 · 2023-04-09推送

deep-learning pytorch

2023-04-09

最近推送

7

LiuHengyu321/IR3D-Bench

[NeurIPS DB 2025] IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering

Python ⭐ 46 ⑂ 0 · 2025-10-15推送

multimodal vlm

2025-10-15

最近推送

8

bowen-upenn/scene_graph_commonsense

[WACV 2025] Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge

Python ⭐ 41 ⑂ 6 MIT · 2024-10-29推送

commonsense-reasoning computer-vision

2024-10-29

最近推送

9

bowen-upenn/Multi-Agent-VQA

[CVPR 2024 CVinW] Multi-Agent VQA: Exploring Multi-Agent Foundation Models on Zero-Shot Visual Question Answering

Python ⭐ 23 ⑂ 1 MIT · 2024-09-22推送

foundation-models large-language-models

2024-09-22

最近推送

10

Apageoflove/VLM-Driving-Scene-Understanding

基于Qwen2.5-VL-3B + QLoRA的智能驾驶场景结构化理解系统

Python ⭐ 12 ⑂ 5 · 25 天前推送

autonomous-driving computer-vision

25 天前

最近推送