Comments (2)
你好,关于你的两个问题我们有以下想法:
- 虽然我们没有在surroundocc里实现无限分辨率,但很容易在现有框架中加入这个功能,只需要对最后输出的occupancy进行三线性插值然后过个mlp即可,可以参考TPVFormer中的实现方式。但需要注意的是,虽然这种方式可以实现无限分辨率,但需要高分辨率的ground truth,使用低分辨率的真值可能会导致效果不好。
- 在surroundocc里我们利用bbox的ground truth将场景和物体(包括静态和动态)分隔开。我们认为网络具备泛化能力,对于没被bbox覆盖的动态异型物,网络也可以重建出来。除此之外,其实用bbox的ground truth去区分动静态只是一种方式,还可以利用一些更加low-level的方式例如场景流去区分。
from surroundocc.
@weiyithu 感謝你的回覆
- 看了一下 TPVFormer 的作法,的確是可以很容易套用到 surroundocc 上。在 TPVFormer 裡面過 mlp 的輸出是由單一 frame 的 lidar 稀疏點來進行監督,所以沒有分辨率的問題,如果无限分辨率也要套用 dense occupancy 監督這的確是要注意的一個點。
- 關於這個問題,比較擔心的不是泛化能力的問題,而是產生真值得時候,如果有动态异型物沒有被bbox覆盖,那會導致 voxel grid 的ground truth 會有這些异型物的殘影。不過透過其他像场景流的方法來區別静动态的確也是一個方向。
from surroundocc.
Related Issues (20)
- could you please provide a result on occ3d-nuscenes? HOT 1
- How to perform OCC prediction using only the front camera? HOT 4
- 关于optimizer和frozen_stage的设置 HOT 2
- Training with my own data. HOT 1
- 算法在orin上有测试过么? HOT 3
- pip install mayavi error HOT 1
- 在运行Train SurroundOcc时候发生的报错 HOT 2
- 关于是否使用关键帧生成gt HOT 1
- 安装chamfer失败 HOT 2
- 训练过程中未知错误 HOT 1
- bbox in non-keyframes HOT 1
- RuntimeError: CUDA error: invalid device function HOT 1
- How big is this file (ertice_train.tar.gz) after extracting
- Some problems I met when I started to train with mini-dataset
- Problems about inference on template data HOT 2
- Algorithm deployment issues
- inference error
- fp16 went to NaN
- About GT generation with own data
- 评价指标计算
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from surroundocc.